CN115018370A - Full wake-based simulation control method and device for offshore wind farm - Google Patents
Full wake-based simulation control method and device for offshore wind farm Download PDFInfo
- Publication number
- CN115018370A CN115018370A CN202210752655.9A CN202210752655A CN115018370A CN 115018370 A CN115018370 A CN 115018370A CN 202210752655 A CN202210752655 A CN 202210752655A CN 115018370 A CN115018370 A CN 115018370A
- Authority
- CN
- China
- Prior art keywords
- wind farm
- wind
- fan
- objective function
- full
- 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 32
- 238000004088 simulation Methods 0.000 title claims abstract description 16
- 238000005457 optimization Methods 0.000 claims abstract description 42
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 24
- 238000012423 maintenance Methods 0.000 claims abstract description 17
- 230000006870 function Effects 0.000 claims description 32
- 238000012549 training Methods 0.000 claims description 9
- 238000012360 testing method Methods 0.000 claims description 6
- 238000004590 computer program Methods 0.000 claims description 5
- 238000007781 pre-processing Methods 0.000 claims description 4
- 230000004044 response Effects 0.000 claims description 4
- 238000013528 artificial neural network Methods 0.000 claims description 3
- 238000011478 gradient descent method Methods 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 230000003068 static effect Effects 0.000 claims 1
- 230000001360 synchronised effect Effects 0.000 claims 1
- 230000003993 interaction Effects 0.000 abstract description 5
- 238000010248 power generation Methods 0.000 abstract description 5
- 239000002245 particle Substances 0.000 description 12
- 238000010586 diagram Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 230000003044 adaptive effect Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000008447 perception Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000004075 alteration Effects 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 238000011217 control strategy Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012216 screening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06312—Adjustment or analysis of established resource schedule, e.g. resource or task levelling, or dynamic rescheduling
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
- G06Q10/06313—Resource planning in a project environment
-
- 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
-
- 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
- Y02E40/00—Technologies for an efficient electrical power generation, transmission or distribution
- Y02E40/10—Flexible AC transmission systems [FACTS]
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- General Physics & Mathematics (AREA)
- Strategic Management (AREA)
- Health & Medical Sciences (AREA)
- Entrepreneurship & Innovation (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Biophysics (AREA)
- Mathematical Physics (AREA)
- Game Theory and Decision Science (AREA)
- Biomedical Technology (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Development Economics (AREA)
- Educational Administration (AREA)
- Biodiversity & Conservation Biology (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
According to the simulation control method, device, equipment and storage medium of the offshore wind farm based on the full-field wake flow, the requirement of power grid dispatching is obtained, forecasting is carried out based on a target SDAE to obtain the forecasting full-field power of the wind farm, an optimization objective function of STATCOM in the wind farm is constructed according to the forecasting full-field power and the requirement of the power grid dispatching, the optimization objective function is solved based on an optimization algorithm to obtain the control parameters of each fan in the wind farm, the control parameters are transmitted to an offshore wind farm operation and maintenance dispatching control system, and the control parameters of each fan are issued to each fan through the offshore wind farm operation and maintenance dispatching control system to control each fan. Therefore, the dynamic wake field accurate simulation is realized, the group control efficiency is improved, the interaction and the cooperation among the fans are enhanced, and the maximization of the power generation efficiency is realized.
Description
Technical Field
The application relates to the field of wind power generation, in particular to a full-field wake-based simulation control method, device, equipment and storage medium for an offshore wind farm.
Background
According to the traditional wind power plant control system, limited domain information acquisition of a wind power plant can be realized only in the aspect of perception, a unified control mode is adopted for each single machine, the influence of tail flow dynamic distribution among units in the plant is ignored, interaction, group level coordination and field level coordination among fans are lacked, and therefore consistency and cooperativity are lacked in control behaviors, so that consistency and accuracy between the fans cannot be corrected timely, and the generated power cannot be maximized in the whole field. Therefore, a simulation control method based on the full-field wake flow is needed to accurately simulate the dynamic wake flow field and further uniformly control the fans in the wind power plant control system.
Disclosure of Invention
The application provides a full wake-based simulation control method, device, equipment and storage medium for an offshore wind farm, so as to accurately simulate a dynamic wake field and uniformly control fans in a wind farm control system.
An embodiment of a first aspect of the present application provides an offshore wind farm simulation control method based on full wake, including:
acquiring the demand of power grid dispatching;
predicting based on a target stack automatic encoding machine SDAE to obtain the predicted full-field power of the wind power plant;
constructing an optimization objective function of the STATCOM in the wind power plant according to the predicted full-field power and the demand of power grid dispatching;
solving the optimization objective function based on an optimization algorithm to obtain control parameters of each fan in the wind power plant, and transmitting the control parameters to an operation and maintenance scheduling control system of the offshore wind power plant;
and issuing the control parameters of each fan to each fan through the operation and maintenance scheduling control system of the offshore wind farm so as to control each fan.
The embodiment of the second aspect of the present application provides an offshore wind farm based on a full wake simulation control device, including:
the acquisition module is used for acquiring the requirement of power grid dispatching;
the prediction module is used for predicting based on a target stack automatic encoding machine SDAE to obtain the predicted full-field power of the wind power plant;
the building module is used for building an optimization objective function of the STATCOM in the wind power plant according to the predicted full-field power and the demand of power grid dispatching;
and the processing module is used for solving the optimization objective function based on an optimization algorithm to obtain the control parameters of each fan in the wind power plant.
A computer device according to an embodiment of the third aspect of the present application includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the method according to the first aspect is implemented.
A computer storage medium according to an embodiment of a fourth aspect of the present application, wherein the computer storage medium stores computer-executable instructions; the computer executable instructions, when executed by a processor, are capable of performing the method of the first aspect as described above.
The technical scheme provided by the embodiment of the application at least has the following beneficial effects:
the method, the device, the equipment and the storage medium for simulating and controlling the offshore wind farm based on the full-field wake flow acquire the requirement of power grid dispatching, predict based on a target SDAE to acquire the predicted full-field power of the wind farm, construct an optimization objective function of STATCOM in the wind farm according to the predicted full-field power and the requirement of power grid dispatching, solve the optimization objective function based on an optimization algorithm to acquire control parameters of each fan in the wind farm, transmit the control parameters to an offshore wind farm operation and maintenance dispatching control system, and transmit the control parameters of each fan to each fan through the offshore wind farm operation and maintenance dispatching control system to control each fan. Therefore, the optimization objective function of the STATCOM in the wind power plant is constructed by predicting the full-field power of the wind power plant and according to the predicted full-field power and the demand of power grid dispatching, so that the dynamic wake field can be accurately simulated, and the control parameters of all the fans in the wind power plant can be obtained. Meanwhile, the consistency and the accuracy between the measurement of the wind turbines can be corrected in time through an operation and maintenance scheduling control system of the offshore wind farm, the farm group control efficiency is improved, the interaction and the cooperation between the wind turbines are enhanced, and the maximization of the power generation efficiency is realized.
Additional aspects and advantages of the present application will be set forth in part in the description which follows and, in part, will be obvious from the description, or may be learned by practice of the present application.
Drawings
The foregoing and/or additional aspects and advantages of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic flow diagram of a full wake-based simulation control method for an offshore wind farm according to the present application;
fig. 2 is a schematic structural diagram of an offshore wind farm based on full wake simulation control device according to the present application.
Detailed Description
Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The method and the device for simulating and controlling the offshore wind farm based on the full wake flow in the embodiment of the application are described below with reference to the accompanying drawings.
Example one
Fig. 1 is a schematic flow chart of a method for simulating control of an offshore wind farm based on full-field wake flow according to an embodiment of the present application, and as shown in fig. 1, the method may include:
In an embodiment of the present application, a demand for grid dispatching may be obtained through user input.
And 102, predicting based on a target SDAE (stacked automatic encoder) to obtain the predicted full-field power of the wind power plant.
In an embodiment of the present application, the SDAE may predict the wind speed and the wind direction based on the input measured values of the wind speed and the wind direction to obtain corresponding predicted values, and then iteratively calculate a wake flow dynamic distribution in a future time domain, so as to calculate the generated power and the yaw angle of the wind turbine.
Specifically, in an embodiment of the present application, for any wind turbine j, the corresponding dynamic wind speed V is obtained through calculation according to the wake flow dynamic distribution of the future time domain j (t) and the corresponding capture power can be calculated by the following formula.
Wherein, C p (a j (t)) is the power factor of the fan, determined by the control strategy of the fan, assuming that the fan is an ideal fan and the fan is in maximum power capture operationAt this time C p The relationship to a is:
C P (a j (t))＝4a j (t)[1-a j (t)] 2
and the total capture power of the wind power plant is the sum of the capture power of each fan, and the capture power of the wind power plant is as follows:
and n is the total number of the fans.
Further, in an embodiment of the disclosure, after the wind farm operates for a period of time, the output of the wind turbine may be analyzed based on the obtained data, so as to obtain an actually operating (wind speed-wind direction-power) power curve model, thereby predicting the full-field power of the wind farm.
In an embodiment of the present application, the prediction is performed based on SDAE to obtain the predicted full field power of the wind farm, and before the prediction, the method may further include the following steps:
and step 1021, acquiring a wake flow original data set.
In an embodiment of the present application, the wake original data set may include: measured data sets and historical data sets.
Specifically, in an embodiment of the present application, the measured data set may include: actually measuring wind speed, wind direction and pitch angle; the historical data set may include: wind speed, wind direction, pitch angle.
And step 1022, preprocessing the wake flow original data set.
In an embodiment of the present application, a method for preprocessing a wake original data set may include at least one of:
interpolating data;
screening a sample;
correcting data;
and (6) normalizing the data.
And 1023, dividing the preprocessed wake flow original data set into a training set and a testing set.
And step 1024, inputting a training set, and performing layer-by-layer training through the DAE to obtain network parameters of each layer.
Step 1025, initialize the network of the stack autocoder and fine tune.
And step 1026, initializing the deep neural network by using each layer of network parameters, and iterating the network weight by a small batch gradient descent method in a test set and a BP algorithm until convergence to obtain the target stacking automatic coding machine.
In one embodiment of the application, prediction is performed based on a target stack automatic coding machine SDAE to obtain the predicted full-field power of a wind power plant, and input information of a prediction model is increased, so that a learning structure of one-to-one mapping of a traditional prediction model is changed, prediction of large-scale offshore wind power plant flow field correlation and unit output correlation is further achieved, and meanwhile, the learning capacity of a traditional modeling algorithm on wind power plant wake big data characteristics is improved by an adopted deep learning algorithm.
And 103, constructing an optimization objective function of the STATCOM in the wind power plant according to the requirements of the predicted full-field power and the power grid dispatching.
In an embodiment of the application, a STATCOM is equipped in a wind farm, a plurality of PI controllers are embedded in a STATCOM control system, and the design of parameters of each PI controller directly influences the control performance of the STATCOM. And in one embodiment of the application, the DFIG-based wind power plant level output characteristics containing the STATCOM and the PCC voltage dynamic response are used as performance indexes, and parameters are designed according to the time multiplied by the error absolute value integration criterion according to the requirements of predicting the full-field power and power grid dispatching.
Wherein,
is the integral of the absolute error of the active power of the DFIG generator multiplied by the time,
is the integral of the absolute error of the dc bus voltage multiplied by time,
the absolute error of the voltage of the common connection point is multiplied by the integral of time, J' represents the comprehensive performance index, T is the dynamic response adjustment time, q 1 、q 2 In order to be a weight factor, the weight factor,
for optimizing the objective function, the superscript denotes the theoretical reference value.
And step 104, solving the optimization objective function based on the optimization algorithm to obtain control parameters of each fan in the wind power plant, and transmitting the control parameters to the operation and maintenance scheduling control system of the offshore wind power plant.
In one embodiment of the present disclosure, solving the optimization objective function based on an optimization algorithm to obtain control parameters of each fan in the wind farm includes: and solving the optimized objective function based on the particle swarm PSO algorithm to obtain the control parameters of each fan in the wind power plant.
Specifically, in an embodiment of the present disclosure, solving the optimization objective function based on the particle swarm PSO algorithm to obtain the control parameter of each fan in the wind farm may include the following steps:
step 1041, determining an update equation of the particle:
v j (t+1)＝ωv j (t)+c 1 r 1 [p j (t)-x j (t)]+
c 2 r 2 [p g (t)-x j (t)]+c 2 r 3 [p k (t)-x j (t)]+
c 1 r 1 [p j (t-1)-x j (t-1)]+c 2 r 2 [p g (t-1)-x j (t-1)]+
c 2 r 3 [p k (t-1)-x j (t-1)]
wherein v is j (t) is the moving speed of the particle j in the t generation, omega is the inertia weight for controlling and improving the optimization efficiency of the algorithm, c 1 As a cognition factor, c 2 Is a social coefficient, p j (t) is the individual historical optimal position of the particle j up to the tth generation, the position of the particle j at the tth generation, the global historical optimal position up to the tth generation, p k (t) local optimization History optimal position until the tth Generation, r 1 、r 2 、r 3 To obey [0, 1]Uniformly distributed random numbers.
1042, adjusting the particles according to an inertial weight adaptive decreasing strategy, wherein the inertial weight adaptive decreasing strategy is as follows:
ω＝ω max exp(-30t/T)
wherein, ω is max The maximum inertia weight is selected in the range of 0.8-0.95, T is the current evolutionary iteration number, and T is the maximum evolutionary iteration number of the algorithm.
In an embodiment of the present disclosure, the particle swarm PSO algorithm further includes a constraint condition, where the constraint condition is:
wherein (x) i ,y i ) The position of the wind turbine is m which is the diameter multiple of the impeller of the wind turbine, the main wind direction is generally 5-7, the non-main wind direction is 3-5, and D is the impeller straight directionAnd (4) diameter.
In an embodiment of the disclosure, each particle in the particle swarm PSO algorithm may be adjusted in motion according to its own experience, and in combination with the iteration and the entire population situation at this time, the iteration situation at the previous time is considered, so that not only are the perception degree and the search capability of the particle and the population improved, but also the diversity of the particle is increased, thereby effectively avoiding the search from being trapped in local minimization.
And 105, issuing the control parameters of each fan to each fan through the operation and maintenance scheduling control system of the offshore wind farm so as to control each fan.
According to the simulation control method, device, equipment and storage medium of the offshore wind farm based on the full-field wake flow, the requirement of power grid dispatching is obtained, the prediction is carried out based on a target stacking automatic coding machine SDAE, the predicted full-field power of the wind farm is obtained, an optimization objective function of STATCOM in the wind farm is constructed according to the predicted full-field power and the requirement of the power grid dispatching, the optimization objective function is solved based on an optimization algorithm, the control parameters of all the fans in the wind farm are obtained and transmitted to an offshore wind farm operation and maintenance dispatching control system, and the control parameters of all the fans are issued to all the fans through the offshore wind farm operation and maintenance dispatching control system so as to control all the fans. Therefore, the optimization objective function of the STATCOM in the wind power plant is constructed by predicting the full-field power of the wind power plant and according to the predicted full-field power and the demand of power grid dispatching, so that the dynamic wake field can be accurately simulated, and the control parameters of all the fans in the wind power plant can be obtained. Meanwhile, the consistency and accuracy of measurement among the fans can be corrected in time through the operation, maintenance, scheduling and control system of the offshore wind farm, the farm group control efficiency is improved, the interaction and cooperation among the fans are enhanced, and the maximization of the power generation efficiency is realized.
Example two
Fig. two is a schematic structural diagram of an analog control device based on full wake flow for an offshore wind farm according to the present application, as shown in fig. 2, the analog control device may include:
an obtaining module 201, configured to obtain a demand of power grid scheduling;
the prediction module 202 is used for predicting based on the target stack automatic coding machine SDAE to obtain the predicted full-field power of the wind power plant;
the building module 203 is used for building an optimization objective function of the STATCOM in the wind power plant according to the requirements of predicting the whole-field power and power grid dispatching;
and the processing module 204 is configured to solve the optimization objective function based on an optimization algorithm to obtain control parameters of each fan in the wind farm.
The method, the device, the equipment and the storage medium for simulating and controlling the offshore wind farm based on the full-field wake flow acquire the requirement of power grid dispatching, predict based on a target stack automatic coding machine SDAE to acquire the predicted full-field power of the wind farm, construct an optimization objective function of STATCOM in the wind farm according to the predicted full-field power and the requirement of the power grid dispatching, solve the optimization objective function based on an optimization algorithm to acquire control parameters of each fan in the wind farm, transmit the control parameters to an offshore wind farm operation and maintenance dispatching control system, and transmit the control parameters of each fan to each fan through the offshore wind farm operation and maintenance dispatching control system to control each fan. Therefore, the optimization objective function of the STATCOM in the wind power plant is constructed by predicting the full-field power of the wind power plant and according to the predicted full-field power and the demand of power grid dispatching, so that the dynamic wake field can be accurately simulated, and the control parameters of all the fans in the wind power plant can be obtained. Meanwhile, the consistency and the accuracy between the measurement of the wind turbines can be corrected in time through an operation and maintenance scheduling control system of the offshore wind farm, the farm group control efficiency is improved, the interaction and the cooperation between the wind turbines are enhanced, and the maximization of the power generation efficiency is realized.
In order to implement the above embodiments, the present disclosure also provides a computer device.
The computer device provided by the embodiment of the disclosure comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, and when the processor executes the computer program, the method shown in fig. 1 can be realized.
In order to implement the above embodiments, the present disclosure also provides a computer storage medium.
The computer storage medium provided by the embodiment of the present disclosure stores computer executable instructions; the computer-executable instructions, when executed by a processor, enable the method illustrated in fig. 1 to be implemented.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present application in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present application.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. An analog control method of an offshore wind farm based on full-field wake flow, wherein the wind farm comprises a static synchronous compensator STATCOM, and the method comprises the following steps:
acquiring the demand of power grid dispatching;
predicting based on a target stack automatic encoding machine SDAE to obtain the predicted full field power of the wind power plant;
constructing an optimization objective function of the STATCOM in the wind power plant according to the predicted full-field power and the demand of power grid dispatching;
solving the optimization objective function based on an optimization algorithm to obtain control parameters of each fan in the wind power plant, and transmitting the control parameters to an operation and maintenance scheduling control system of the offshore wind power plant;
and issuing the control parameters of each fan to each fan through the operation and maintenance scheduling control system of the offshore wind farm so as to control each fan.
2. The analog control method according to claim 1, characterized in that said prediction based on a target stacked autocoder SDAE results in a predicted full field power of said wind farm, before said method further comprises:
acquiring a wake flow original data set;
preprocessing the wake flow original data set;
dividing the preprocessed wake flow original data set into a training set and a test set;
inputting the training set, and performing layer-by-layer training through DAE to obtain network parameters of each layer;
initializing a network of the stacking automatic coding machine and carrying out fine adjustment;
and initializing the deep neural network by using the network parameters of each layer, and iterating the network weight by a small batch gradient descent method in a test set and a BP algorithm until convergence to obtain the target stacking automatic coding machine.
3. The simulation control method of claim 1, wherein the optimization objective function comprises:
wherein,
is the integral of the absolute error of the active power of the DFIG generator multiplied by the time,
is the integral of the absolute error of the dc bus voltage multiplied by time,
the absolute error of the voltage of the common connection point is multiplied by the integral of time, J' represents the comprehensive performance index, T is the dynamic response adjustment time, q 1 、q 2 Is a weighting factor.
4. The simulation control method according to claim 1, wherein solving the optimization objective function based on an optimization algorithm to obtain control parameters of each wind turbine in the wind farm comprises: and solving the optimized objective function based on a PSO algorithm and constraint conditions to obtain control parameters of each fan in the wind power plant.
5. The simulation control method according to claim 4, wherein the constraint condition is:
wherein (x) i ,y i ) The position of the wind turbine is shown in the specification, m is the diameter multiple of the impeller of the wind turbine, the main wind direction is generally 5-7, the non-main wind direction is 3-5, and D is the diameter of the impeller.
6. An offshore wind farm full wake based analog control device, the device comprising:
the acquisition module is used for acquiring the requirement of power grid dispatching;
the prediction module is used for predicting based on a target stack automatic encoding machine SDAE to obtain the predicted full-field power of the wind power plant;
the building module is used for building an optimization objective function of the STATCOM in the wind power plant according to the predicted full-field power and the power grid dispatching requirement;
and the processing module is used for solving the optimization objective function based on an optimization algorithm to obtain the control parameters of each fan in the wind power plant.
7. The analog control device of claim 6, wherein the device is further configured to:
acquiring a wake flow original data set;
preprocessing the wake flow original data set;
dividing the preprocessed wake flow original data set into a training set and a test set;
inputting the training set, and performing layer-by-layer training through DAE to obtain network parameters of each layer;
initializing a network of the stacking automatic coding machine and carrying out fine adjustment;
and initializing the deep neural network by using the network parameters of each layer, and iterating the network weight by a small batch gradient descent method in a test set and a BP algorithm until convergence to obtain the target stacking automatic coding machine.
8. The simulation control device of claim 6, wherein the optimization objective function comprises:
wherein,
is the integral of the absolute error of the active power of the DFIG generator multiplied by the time,
is the integral of the absolute error of the dc bus voltage multiplied by time,
the absolute error of the voltage of the common connection point is multiplied by the integral of time, J' represents the comprehensive performance index, T is the dynamic response adjustment time, q 1 、q 2 Is a weighting factor.
9. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method according to any one of claims 1-5 when executing the program.
10. A computer storage medium, wherein the computer storage medium stores computer-executable instructions; the computer-executable instructions, when executed by a processor, are capable of performing the method of any one of claims 1-5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210752655.9A CN115018370A (en) | 2022-06-29 | 2022-06-29 | Full wake-based simulation control method and device for offshore wind farm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210752655.9A CN115018370A (en) | 2022-06-29 | 2022-06-29 | Full wake-based simulation control method and device for offshore wind farm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115018370A true CN115018370A (en) | 2022-09-06 |
Family
ID=83079605
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210752655.9A Pending CN115018370A (en) | 2022-06-29 | 2022-06-29 | Full wake-based simulation control method and device for offshore wind farm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115018370A (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102142103A (en) * | 2011-04-15 | 2011-08-03 | 河海大学 | Real-coded genetic algorithm-based optimizing method for micrositing of wind power station |
| CN109782583A (en) * | 2019-01-18 | 2019-05-21 | 中国电力科学研究院有限公司 | A kind of wind power plant PI attitude conirol method and apparatus |
| US20190226454A1 (en) * | 2016-09-16 | 2019-07-25 | Vestas Wind Systems A/S | Reactive power production of wind turbine generators within wind wake zone |
| CN110535174A (en) * | 2019-07-23 | 2019-12-03 | 电子科技大学 | A kind of active power controller method considering wind power plant fatigue load distribution and production capacity |
| CN111339713A (en) * | 2020-03-13 | 2020-06-26 | 上海电气风电集团股份有限公司 | Optimal design method and system for wind power plant, electronic device and storage medium |
| WO2021253291A1 (en) * | 2020-06-17 | 2021-12-23 | 上海电气风电集团股份有限公司 | Wind farm layout optimization method and optimization system, and computer-readable storage medium |
-
2022
- 2022-06-29 CN CN202210752655.9A patent/CN115018370A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102142103A (en) * | 2011-04-15 | 2011-08-03 | 河海大学 | Real-coded genetic algorithm-based optimizing method for micrositing of wind power station |
| US20190226454A1 (en) * | 2016-09-16 | 2019-07-25 | Vestas Wind Systems A/S | Reactive power production of wind turbine generators within wind wake zone |
| CN109782583A (en) * | 2019-01-18 | 2019-05-21 | 中国电力科学研究院有限公司 | A kind of wind power plant PI attitude conirol method and apparatus |
| CN110535174A (en) * | 2019-07-23 | 2019-12-03 | 电子科技大学 | A kind of active power controller method considering wind power plant fatigue load distribution and production capacity |
| CN111339713A (en) * | 2020-03-13 | 2020-06-26 | 上海电气风电集团股份有限公司 | Optimal design method and system for wind power plant, electronic device and storage medium |
| WO2021253291A1 (en) * | 2020-06-17 | 2021-12-23 | 上海电气风电集团股份有限公司 | Wind farm layout optimization method and optimization system, and computer-readable storage medium |
Non-Patent Citations (3)
| Title |
|---|
| 曹梦娇: ""考虑尾流影响的风电场输出功率优化控制"", 《中国优秀硕士学位论文全文数据库·工程科技Ⅱ辑》, no. 8, 15 August 2019 (2019-08-15), pages 1 - 62 * |
| 李聪等: ""基于SDAE 深度学习与多重集成的风电集群 短期功率预测"", 《高电压技术》, vol. 48, no. 2, 28 February 2022 (2022-02-28), pages 504 - 512 * |
| 顾波等: ""考虑尾流效应的风电场优化控制技术研究"", 《太阳能学报》, vol. 39, no. 2, 28 February 2018 (2018-02-28), pages 359 - 368 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107769254B (en) | A kind of wind-powered electricity generation cluster trajectory predictions and hierarchical control method | |
| Andersson et al. | Wind farm control‐Part I: A review on control system concepts and structures | |
| CN105048499B (en) | Wind-electricity integration real-time scheduling method and system based on Model Predictive Control | |
| CN105046374A (en) | Power interval predication method based on nucleus limit learning machine model | |
| EP3791060B1 (en) | Wind turbine control method | |
| CN109256810B (en) | Multi-objective optimization method considering uncertain cost of fan output | |
| CN107909211B (en) | Wind field equivalent modeling and optimization control method based on fuzzy c-means clustering algorithm | |
| CN102496927A (en) | Wind power station power projection method based on error statistics modification | |
| CN103268366A (en) | Combined wind power prediction method suitable for distributed wind power plant | |
| CN108512258B (en) | Wind power plant active scheduling method based on improved multi-agent consistency algorithm | |
| CN104115166A (en) | A method for computer-assisted determination of the usage of electrical energy produced by a power generation plant, particularly a renewable power generation plant | |
| CN104376389A (en) | Master-slave type micro-grid power load prediction system and master-slave type micro-grid power load prediction method based on load balancing | |
| CN106026084B (en) | A kind of AGC power dynamic allocation methods based on virtual power generation clan | |
| CN114362175B (en) | Wind power prediction method and system based on depth certainty strategy gradient algorithm | |
| CN112001537B (en) | Short-term wind power prediction method based on gray model and support vector machine | |
| CN115333168A (en) | Offshore wind farm field level control strategy based on distributed rolling optimization | |
| CN108196444A (en) | Based on the control of the variable pitch wind energy conversion system of feedback linearization sliding formwork and SCG and discrimination method | |
| Liu et al. | Short-term wind power forecasting based on TS fuzzy model | |
| CN115578016A (en) | Online evaluation method for frequency modulation capability of wind power plant with incomplete model | |
| Poushpas | Wind farm simulation modelling and control | |
| Requate et al. | Active control of the reliability of wind turbines | |
| CN115018370A (en) | Full wake-based simulation control method and device for offshore wind farm | |
| Dimitrov et al. | Wind farm set point optimization with surrogate models for load and power output targets | |
| CN115313527A (en) | Wind power plant active power distribution method considering turbulence wind speed fluctuation | |
| CN115936407A (en) | Power system optimal scheduling method considering new energy uncertainty and storage medium |
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 |