CN116123028A - Wind power plant level MPPT prediction model control method and device - Google Patents
Wind power plant level MPPT prediction model control method and device Download PDFInfo
- Publication number
- CN116123028A CN116123028A CN202211641354.5A CN202211641354A CN116123028A CN 116123028 A CN116123028 A CN 116123028A CN 202211641354 A CN202211641354 A CN 202211641354A CN 116123028 A CN116123028 A CN 116123028A
- Authority
- CN
- China
- Prior art keywords
- wind speed
- wind
- preset duration
- data
- time sequence
- 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 58
- 230000006870 function Effects 0.000 claims description 18
- 238000005457 optimization Methods 0.000 claims description 11
- 238000012549 training Methods 0.000 claims description 10
- 238000004590 computer program Methods 0.000 claims description 9
- 230000004044 response Effects 0.000 claims description 9
- 238000004422 calculation algorithm Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 5
- 238000005096 rolling process Methods 0.000 claims description 4
- 238000005259 measurement Methods 0.000 description 8
- 230000000694 effects Effects 0.000 description 6
- 238000004364 calculation method Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000013136 deep learning model Methods 0.000 description 3
- 238000003491 array Methods 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000009194 climbing Effects 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000013213 extrapolation Methods 0.000 description 1
- 230000002068 genetic effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000002245 particle Substances 0.000 description 1
Images
Classifications
-
- F—MECHANICAL ENGINEERING; LIGHTING; HEATING; WEAPONS; BLASTING
- F03—MACHINES OR ENGINES FOR LIQUIDS; WIND, SPRING, OR WEIGHT MOTORS; PRODUCING MECHANICAL POWER OR A REACTIVE PROPULSIVE THRUST, NOT OTHERWISE PROVIDED FOR
- F03D—WIND MOTORS
- F03D7/00—Controlling wind motors
- F03D7/02—Controlling wind motors the wind motors having rotation axis substantially parallel to the air flow entering the rotor
- F03D7/04—Automatic control; Regulation
- F03D7/042—Automatic control; Regulation by means of an electrical or electronic controller
- F03D7/043—Automatic control; Regulation by means of an electrical or electronic controller characterised by the type of control logic
- F03D7/045—Automatic control; Regulation by means of an electrical or electronic controller characterised by the type of control logic with model-based controls
Landscapes
- Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Sustainable Development (AREA)
- Sustainable Energy (AREA)
- Chemical & Material Sciences (AREA)
- Combustion & Propulsion (AREA)
- Mechanical Engineering (AREA)
- General Engineering & Computer Science (AREA)
- Control Of Eletrric Generators (AREA)
- Wind Motors (AREA)
Abstract
The application provides a wind power plant level MPPT prediction model control method, which relates to the technical field of fan control, wherein the method comprises the following steps: acquiring wind speed field space-time sequence data of a wind power field range with a first preset duration; based on the wind speed field space-time sequence data, predicting by using a trained wind speed prediction model to obtain a wind speed field space-time sequence prediction result of a second preset duration, wherein the second preset duration is adjacent to the first preset duration; and calculating a control quantity sequence in a second preset time length of each fan according to the wind speed field space-time sequence prediction result, and controlling the rotating speed of the fan at the next moment according to the first control quantity in the control quantity sequence. According to the wind turbine control method and device, the rotation speed of the fan can be controlled more optimally, so that the running efficiency of the wind turbine is improved, and wind energy is utilized to the maximum extent.
Description
Technical Field
The application relates to the technical field of fan control, in particular to a wind power plant level MPPT prediction model control method and device.
Background
Wind energy is an energy source with characteristics of randomness, explosiveness and instability, and how to efficiently and stably utilize the wind energy is an important problem for wind energy development. The change of wind speed can cause the change of the rotating speed of the wind turbine, and the wind energy can be utilized to the maximum extent when the tip speed ratio of the wind turbine is at or near the optimal value through proper control because the rotating speed of the wind turbine is variable. The optimal tip speed ratio can be maintained in a wider range, so that the running efficiency of the wind turbine is improved. This control method is called Maximum Power Point Tracking (MPPT).
In the prior art, the common MPPT method is an optimal tip speed ratio method, a power feedback method and a hill climbing algorithm, wherein the power feedback and hill climbing algorithm do not need wind speed information as input, but stability and response speed are relatively poor, in the wind generating set equipped with the laser wind measuring radar at present, the optimal tip speed ratio method can provide more stable control and quicker response, but on one hand, the current wind measuring data mainly come from single-machine equipment, each wind generating set needs to be equipped with the wind measuring radar to realize the control method, on the other hand, the wind measuring data in the traditional scheme only use the last moment data as control input, and are actually controlled based on historical data, and the response speed and stability have further optimized space.
Disclosure of Invention
The present application aims to solve, at least to some extent, one of the technical problems in the related art.
Therefore, a first object of the present application is to provide a control method for a wind farm level MPPT prediction model, which solves the technical problems that the effect is not good enough when single wind measurement data of the existing method is used for wind speed prediction, and further optimized space exists for controlling a wind turbine based on historical data, and the control result of a relatively accurate wind speed prediction result is obtained more quickly and the overshoot is smaller, so that the MPPT control performance of each wind turbine of the wind farm is improved, the rotation speed of the wind turbine is better controlled, the running efficiency of the wind turbine is improved, and the wind energy is utilized to the maximum extent.
A second object of the present application is to provide a wind farm level MPPT prediction model control device.
A third object of the present application is to propose a computer device.
A fourth object of the present application is to propose a non-transitory computer readable storage medium.
To achieve the above objective, an embodiment of a first aspect of the present application provides a method for controlling a wind farm level MPPT prediction model, including: acquiring wind speed field space-time sequence data of a wind power field range with a first preset duration; based on the wind speed field space-time sequence data, predicting by using a trained wind speed prediction model to obtain a wind speed field space-time sequence prediction result of a second preset duration, wherein the second preset duration is adjacent to the first preset duration; and calculating a control quantity sequence in a second preset time length of each fan according to the wind speed field space-time sequence prediction result, and controlling the rotating speed of the fan at the next moment according to the first control quantity in the control quantity sequence.
Optionally, in an embodiment of the present application, after controlling the rotation speed of the fan at the next moment according to the first control amount in the control amount sequence, the method further includes:
and periodically updating the control quantity sequence by adopting a rolling optimization method.
Optionally, in one embodiment of the present application, acquiring wind farm spatiotemporal sequence data of a wind farm range for a first preset duration includes:
acquiring wind speed time sequence data of a first preset duration of a fan through a laser wind measuring radar;
and performing 2D interpolation processing on the wind speed time sequence data of all fans in the wind power plant for a first preset duration to obtain wind speed space-time sequence data of the wind power plant range for the first preset duration.
Optionally, in one embodiment of the present application, before predicting using the trained wind speed prediction model based on the wind speed field spatiotemporal sequence data, the method comprises:
acquiring historical wind speed data measured by each fan of a wind power plant for a first preset duration;
performing 2D interpolation processing on the historical wind speed data to obtain historical wind speed field space-time sequence data of a wind power field range with a first preset duration, wherein the historical wind speed field space-time sequence data comprises historical wind speed data of areas where all fans are located;
establishing a data set according to the historical wind speed data of the area where each fan is located, and randomly sampling according to the data set by taking the first preset duration and the second preset duration as time sequence lengths to obtain an area wind speed prediction data set;
and training the wind speed prediction model by using the regional wind speed prediction data set to obtain a trained wind speed prediction model.
Optionally, in one embodiment of the present application, training the wind speed prediction model using the regional wind speed prediction dataset to obtain a trained wind speed prediction model, including;
taking data in a first preset duration in the regional wind speed prediction data set as input, taking data in a second preset duration in the regional wind speed prediction data set as expected output, training a wind speed prediction model to obtain a trained wind speed prediction model, wherein the trained wind speed prediction model is input into wind speed field space-time sequence data in the first preset duration, and outputting a wind speed field space-time sequence prediction result in the second preset duration.
Optionally, in an embodiment of the present application, calculating the control quantity sequence in the second preset duration of each fan according to the wind speed field space-time sequence prediction result includes:
obtaining an optimal rotating speed curve of each fan according to a wind speed field space-time sequence prediction result and an inherent optimal power curve of the fan;
initializing control quantity of each fan within a second preset time period, and constructing an objective function according to the optimal rotating speed curve and the control quantity within the second preset time period;
and optimizing the control quantity by adopting an optimization algorithm, and outputting the control quantity with the minimum objective function as an optimal control quantity to obtain a control quantity sequence of each fan within a second preset duration.
Alternatively, in one embodiment of the present application, the objective function is expressed as:
wherein L represents an objective function, N represents the number of control moments within a second preset time period,
indicating the optimal rotation speed corresponding to the wind speed at each moment in the second preset time period,/for each moment>
And representing a response result corresponding to the control quantity at each moment in the second preset time.
To achieve the above object, an embodiment of a second aspect of the present application provides a wind farm level MPPT prediction model control device, including:
the acquisition module is used for acquiring wind speed field space-time sequence data of a wind power field range with a first preset duration;
the prediction module is used for predicting by using a trained wind speed prediction model based on the wind speed field space-time sequence data to obtain a wind speed field space-time sequence prediction result of a second preset duration, wherein the second preset duration is adjacent to the first preset duration;
the control module is used for calculating a control quantity sequence in a second preset duration of each fan according to the wind speed field space-time sequence prediction result and controlling the rotating speed of the fan at the next moment according to the control quantity of the first control quantity in the control quantity sequence.
To achieve the above objective, an embodiment of a third aspect of the present application provides a computer device, including a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the control method of the wind farm level MPPT prediction model according to the above embodiment when executing the computer program.
To achieve the above object, a fourth aspect of the present application proposes a non-transitory computer-readable storage medium, which when executed by a processor, is capable of executing a wind farm-level MPPT prediction model control method.
According to the control method, the device, the computer equipment and the non-transitory computer readable storage medium for the wind power plant level MPPT prediction model, the technical problems that the effect is not good enough when single wind measurement data of the existing method is used for wind speed prediction, and further optimized space exists for wind turbine control only based on historical data are solved, the control result with quicker speed and smaller overshoot is obtained through the relatively accurate wind speed prediction result, the MPPT control performance of each wind turbine of the wind power plant is improved, the rotating speed of the wind turbines is controlled better, the running efficiency of the wind turbines is improved, and wind energy is utilized to the maximum extent.
Additional aspects and advantages of the 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 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, in which:
fig. 1 is a flowchart of a control method for a wind farm level MPPT prediction model according to an embodiment of the present application;
fig. 2 is a control architecture exemplary diagram of a control method of a wind farm level MPPT prediction model according to an embodiment of the application;
FIG. 3 is an exemplary diagram of data samples, input data, and output data of a wind speed prediction model of a wind farm level MPPT prediction model control method of embodiments of the present application;
FIG. 4 is an input and output example diagram of a trained wind speed prediction model of a wind farm level MPPT prediction model control method of an embodiment of the present application;
fig. 5 is a comparison chart of the optimal rotation speed curve of the fan and the response results under other control sequences of the wind farm level MPPT prediction model control method according to the embodiment of the application;
fig. 6 is a schematic structural diagram of a wind farm level MPPT prediction model control device according to a second embodiment of the present application.
Detailed Description
Embodiments of the present application are described in detail below, examples of which are illustrated in the accompanying drawings, wherein the same or similar reference numerals refer to the same or similar elements or elements having the same or similar functions throughout. The embodiments described below by referring to the drawings are exemplary and intended for the purpose of explaining the present application and are not to be construed as limiting the present application.
The wind speed information required by MPPT (maximum power point tracking) control of the existing wind generating set comes from the local equipment, the data of other site anemometers are not utilized, the effect is not good enough when the single machine anemometer data is used for wind speed prediction, the input data of the control operation is historical data, and the control based on the historical data only has a space for further optimization. If the wind measuring data of each station can be uploaded to the upper computer, the obtained wind measuring data is applied to station-level control. The station-level wind measurement data contains larger information quantity, is more suitable for being applied to adjacent wind speed prediction, and a wind speed prediction result can provide more sufficient information for MPPT control, so that more optimal control is realized.
According to the control method for the wind power plant level MPPT prediction model, wind power plant wind measurement data are subjected to station level prediction and then distributed to all wind driven generators for MPPT prediction model control, more accurate wind speed prediction results can be obtained through station level extrapolation of wind speed, and on the basis of relatively accurate wind speed prediction results, the prediction model control can obtain control results which are faster and smaller in overshoot, so that MPPT control performance of all wind driven generators of the wind power plant is improved.
The following describes a wind farm level MPPT prediction model control method and device according to the embodiments of the present application with reference to the accompanying drawings.
Fig. 1 is a flowchart of a control method for a wind farm level MPPT prediction model according to an embodiment of the present application.
As shown in fig. 1, the wind farm level MPPT prediction model control method includes the following steps:
and 103, calculating a control quantity sequence in a second preset duration of each fan according to the wind speed field space-time sequence prediction result, and controlling the rotating speed of the fan at the next moment according to the first control quantity in the control quantity sequence.
According to the wind power plant level MPPT prediction model control method, wind power plant space-time sequence data of a wind power plant range with a first preset duration are obtained; based on the wind speed field space-time sequence data, predicting by using a trained wind speed prediction model to obtain a wind speed field space-time sequence prediction result of a second preset duration, wherein the second preset duration is adjacent to the first preset duration; and calculating a control quantity sequence in a second preset time length of each fan according to the wind speed field space-time sequence prediction result, and controlling the rotating speed of the fan at the next moment according to the first control quantity in the control quantity sequence. Therefore, the technical problems that when single-machine wind measurement data of the existing method is used for wind speed prediction, the effect is not good enough, and further optimized space exists for controlling the wind turbines based on historical data only can be solved, the control results of being quicker and smaller in overshoot are obtained through the relatively accurate wind speed prediction results, the MPPT control performance of each wind turbine of a wind power plant is improved, the rotating speed of the wind turbines is controlled better, the running efficiency of the wind turbines is improved, and wind energy is utilized to the maximum extent.
According to the wind power plant level wind data prediction method based on space-time sequence data deep learning, wind power plant prediction is conducted on a 2D area through collecting wind power plant level wind data of each fan station, and then the wind power plant level wind data is distributed to a control framework of each unit controller through prediction data to conduct fan rotating speed control. As shown in fig. 2, wind speed is measured by wind-measuring radars of all fan stations, and wind-measuring data are transmitted to an upper computer by a DTU (data transmission unit); converting time sequence wind speed data of each fan station into space-time sequence data by the upper computer, namely carrying out 2D interpolation on the whole wind power plant range in each time step based on wind measurement data of each fan station to obtain wind power plant information in the wind power plant range in each time step; the upper computer predicts the time-space sequence data of the historical wind speed field in the time length of T1 to obtain a wind field time-space sequence prediction result in the time length of T2 in the future; and distributing the wind speed time series data of each wind power plant position in the prediction result to a control optimizer of each fan, performing control optimization calculation, and submitting the control optimization result to a controller for control.
Further, in the embodiment of the present application, after controlling the rotation speed of the fan at the next moment according to the first control amount in the control amount sequence, the method further includes:
and periodically updating the control quantity sequence by adopting a rolling optimization method.
In the embodiment of the application, although the control quantity sequence given by the optimization algorithm is the control quantity of all time steps in the prediction time period T, the method is performed in a rolling way, and the same calculation is performed in the next time step to update the subsequent control quantity, so that the result of each calculation is only the first control quantity of the control sequence, namely, the control quantity of the next control time step is actually used for control. For example, t1 and t2 are two control time steps, wind speed is predicted at time t1, control quantity calculation is performed, control is performed at time t2 by using the control quantity calculated at time t1, next round of prediction and control quantity calculation is performed, a new control quantity sequence is obtained, and the cycle is circulated.
Further, in the embodiment of the present application, acquiring wind farm space-time sequence data of a wind farm range for a first preset duration includes:
acquiring wind speed time sequence data of a first preset duration of a fan through a laser wind measuring radar;
and performing 2D interpolation processing on the wind speed time sequence data of all fans in the wind power plant for a first preset duration to obtain wind speed space-time sequence data of the wind power plant range for the first preset duration.
In the embodiment of the application, the laser wind-finding radar of the fans is used for acquiring the wind speed time sequence data of all fans in the wind power plant for a first preset time length; and performing 2D interpolation processing on the wind speed time sequence data of the first preset duration of all fans in the wind power plant to obtain wind speed space-time sequence data of the wind power plant range.
Further, in an embodiment of the present application, before predicting using the trained wind speed prediction model based on the wind speed field spatiotemporal sequence data, the method includes:
acquiring historical wind speed data measured by each fan of a wind power plant for a first preset duration;
performing 2D interpolation processing on the historical wind speed data to obtain historical wind speed field space-time sequence data of a wind power field range with a first preset duration, wherein the historical wind speed field space-time sequence data comprises historical wind speed data of areas where all fans are located;
establishing a data set according to the historical wind speed data of the area where each fan is located, and randomly sampling according to the data set by taking the first preset duration and the second preset duration as time sequence lengths to obtain an area wind speed prediction data set;
and training the wind speed prediction model by using the regional wind speed prediction data set to obtain a trained wind speed prediction model.
In the embodiment of the application, the historical wind speed field space-time sequence data of the wind power field range with the first preset duration comprises historical wind speed data of the region where each fan of the wind power field is located; collecting historical wind speed data of the area where each fan is located, establishing a data set, taking T1+ T2 as the time sequence length, randomly sampling, taking the sampled data, taking the front T1 time period as a wind speed prediction model for input, taking the rear T2 time period as the expected output of the wind speed prediction model, and obtaining an area wind speed prediction data set. As shown in fig. 3, historical wind speed data of the area where each fan is located is collected, a data sample is established, the time sequence length of T1+ T2 is taken as the time sequence length, random sampling is carried out, the sampled data is input by taking the previous time period of T1 as a wind speed prediction model, and the later time period of T2 is taken as the expected output of the wind speed prediction model.
Further, in the embodiment of the present application, training a wind speed prediction model by using a regional wind speed prediction data set to obtain a trained wind speed prediction model, including;
taking data in a first preset duration in the regional wind speed prediction data set as input, taking data in a second preset duration in the regional wind speed prediction data set as expected output, training a wind speed prediction model to obtain a trained wind speed prediction model, wherein the trained wind speed prediction model is input into wind speed field space-time sequence data in the first preset duration, and outputting a wind speed field space-time sequence prediction result in the second preset duration.
Because the wind measurement data are space-time sequence data, the Conv-LSTM deep learning model is adopted as a wind speed prediction model, the regional wind speed prediction data set is adopted for training, the wind speed space-time sequence data input into the time length T1 are obtained, and the wind speed prediction model of the wind speed space-time sequence prediction result of the time length T2 is output. As shown in fig. 4, the wind speed space-time sequence data with the time length T1 is input into a Conv-LSTM deep learning model, and the Conv-LSTM deep learning model outputs a wind speed space-time sequence prediction result with the time length T2.
Further, in the embodiment of the present application, calculating the control quantity sequence within the second preset duration of each fan according to the wind speed field space-time sequence prediction result includes:
obtaining an optimal rotating speed curve of each fan according to a wind speed field space-time sequence prediction result and an inherent optimal power curve of the fan;
initializing control quantity of each fan within a second preset time period, and constructing an objective function according to the optimal rotating speed curve and the control quantity within the second preset time period;
and optimizing the control quantity by adopting an optimization algorithm, and outputting the control quantity with the minimum objective function as an optimal control quantity to obtain a control quantity sequence of each fan within a second preset duration.
In the embodiment of the application, the pitch angle of the direct-drive fan is kept unchanged in the power tracking stage, and the electromagnetic torque is controlled mainly through controlling Iq (control quantity) of the converter so as to control the rotating speed of the motor. After the wind speed is predicted, an optimal rotating speed curve corresponding to the wind speed can be obtained through an inherent optimal power curve of the fan, different control response curves can be obtained through adjusting the control quantity Iq in each time step in a T2 time period after a predicted time point, and the closer the curve is to the optimal rotating speed curve corresponding to the predicted wind speed, the better the control effect is. As shown in fig. 5, an optimal rotation speed curve corresponding to the wind speed is obtained through an inherent optimal power curve of the fan, and different control response curves can be obtained through adjusting the control quantity Iq in each time step in a T2 time period after the predicted time point.
And optimizing the control quantity by adopting an optimization algorithm (particle swarm, genetic algorithm and the like) so as to minimize the objective function L, and outputting the control quantity as an optimal control quantity to obtain a control quantity sequence within a second preset duration.
Further, in the embodiment of the present application, the objective function is expressed as:
wherein L represents an objective function, N represents the number of control moments, i.e. the number of control time steps,
indicating the optimal rotation speed corresponding to the wind speed at each moment in the second preset time period,/for each moment>
And representing a response result corresponding to the control quantity at each moment in the second preset time.
Fig. 6 is a schematic structural diagram of a wind farm level MPPT prediction model control device according to a second embodiment of the present application.
As shown in fig. 6, the wind farm level MPPT prediction model control device includes:
the acquisition module 10 is used for acquiring wind speed field space-time sequence data of a wind power field range with a first preset duration;
the prediction module 20 is configured to predict, based on the wind speed field space-time sequence data, using a trained wind speed prediction model to obtain a wind speed field space-time sequence prediction result of a second preset duration, where the second preset duration is adjacent to the first preset duration;
the control module 30 is configured to calculate a control amount sequence within a second preset duration of each fan according to the wind speed field space-time sequence prediction result, and control the rotation speed of the fan at the next moment according to the control amount of the first one of the control amount sequences.
The wind power plant level MPPT prediction model control device comprises an acquisition module, a control module and a control module, wherein the acquisition module is used for acquiring wind power plant space-time sequence data of a wind power plant range with a first preset duration; the prediction module is used for predicting by using a trained wind speed prediction model based on the wind speed field space-time sequence data to obtain a wind speed field space-time sequence prediction result of a second preset duration, wherein the second preset duration is adjacent to the first preset duration; the control module is used for calculating a control quantity sequence in a second preset duration of each fan according to the wind speed field space-time sequence prediction result and controlling the rotating speed of the fan at the next moment according to the control quantity of the first control quantity in the control quantity sequence. Therefore, the technical problems that when single-machine wind measurement data of the existing method is used for wind speed prediction, the effect is not good enough, and further optimized space exists for controlling the wind turbines based on historical data only can be solved, the control results of being quicker and smaller in overshoot are obtained through the relatively accurate wind speed prediction results, the MPPT control performance of each wind turbine of a wind power plant is improved, the rotating speed of the wind turbines is controlled better, the running efficiency of the wind turbines is improved, and wind energy is utilized to the maximum extent.
In order to implement the above embodiment, the application further provides a computer device, which includes a memory, a processor, and a computer program stored in the memory and capable of running on the processor, where the processor implements the control method of the wind farm level MPPT prediction model according to the above embodiment when executing the computer program.
In order to implement the above embodiment, the application further proposes a non-transitory computer readable storage medium, on which a computer program is stored, which when executed by a processor implements the wind farm level MPPT prediction model control method of the above embodiment.
In the description of the present specification, a description referring to terms "one embodiment," "some embodiments," "examples," "specific examples," 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 present application. In this specification, schematic representations of the above terms are not necessarily directed 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, the different embodiments or examples described in this specification and the features of the different embodiments or examples may be combined and combined by those skilled in the art without contradiction.
Furthermore, the terms "first," "second," and the like, are used for descriptive purposes only and are not to be construed as indicating or implying a relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defining "a first" or "a second" may explicitly or implicitly include at least one such feature. In the description of the present application, the meaning of "plurality" is at least two, such as two, three, etc., unless explicitly defined otherwise.
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 specific logical functions or steps of the process, and additional 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 embodiments of the present application.
Logic and/or steps represented in the flowcharts or otherwise described herein, e.g., a ordered listing of executable instructions for implementing logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer readable medium may even be paper or other suitable medium on which the program is printed, as the program may be electronically captured, via, for instance, optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner, if necessary, and then stored in a computer memory.
It is to be understood that portions of the present application may be implemented in hardware, software, firmware, or a combination thereof. In the above-described embodiments, the various steps or methods may be implemented in software or firmware stored in a memory and executed by a suitable instruction execution system. As with the other embodiments, if implemented in hardware, may be implemented using any one or combination of the following techniques, as is well known in the art: discrete logic circuits having logic gates for implementing logic functions on data signals, application specific integrated circuits having suitable combinational logic gates, programmable Gate Arrays (PGAs), field Programmable Gate Arrays (FPGAs), and the like.
Those of ordinary skill in the art will appreciate that all or a portion of the steps carried out in the method of the above-described embodiments may be implemented by a program to instruct related hardware, where the program may be stored in a computer readable storage medium, and where the program, when executed, includes one or a combination of the steps of the method embodiments.
In addition, each functional unit in each embodiment of the present application may be integrated in one processing module, or each unit may exist alone physically, or two or more units may be integrated in one module. The integrated modules may be implemented in hardware or in software functional modules. The integrated modules may also be stored in a computer readable storage medium if implemented in the form of software functional modules and sold or used as a stand-alone product.
The above-mentioned storage medium may be a read-only memory, a magnetic disk or an optical disk, or the like. Although embodiments of the present application have been shown and described above, it will be understood that the above embodiments are illustrative and not to be construed as limiting the application, and that variations, modifications, alternatives, and variations may be made to the above embodiments by one of ordinary skill in the art within the scope of the application.
Claims (10)
1. The wind power plant level MPPT prediction model control method is characterized by comprising the following steps of:
acquiring wind speed field space-time sequence data of a wind power field range with a first preset duration;
based on the wind speed field space-time sequence data, predicting by using a trained wind speed prediction model to obtain a wind speed field space-time sequence prediction result with a second preset duration, wherein the second preset duration is adjacent to the first preset duration;
and calculating a control quantity sequence in a second preset time length of each fan according to the wind speed field space-time sequence prediction result, and controlling the rotating speed of the fan at the next moment according to the first control quantity in the control quantity sequence.
2. The method of claim 1, further comprising, after controlling the rotational speed of the blower at a next time based on a first control in the sequence of control amounts:
and periodically updating the control quantity sequence by adopting a rolling optimization method.
3. The method of claim 1, wherein the acquiring wind farm spatiotemporal sequence data for a wind farm range for a first predetermined duration comprises:
acquiring wind speed time sequence data of a first preset duration of a fan through a laser wind measuring radar;
and performing 2D interpolation processing on the wind speed time sequence data of all fans in the wind power plant for a first preset duration to obtain wind power plant space-time sequence data of the wind power plant range for the first preset duration.
4. The method of claim 1, comprising, prior to predicting using a trained wind speed prediction model based on the wind speed field spatiotemporal sequence data:
acquiring historical wind speed data measured by each fan of a wind power plant for a first preset duration;
performing 2D interpolation processing on the historical wind speed data to obtain historical wind speed field space-time sequence data of the wind power field range with the first preset duration, wherein the historical wind speed field space-time sequence data comprises historical wind speed data of areas where all fans are located;
establishing a data set according to the historical wind speed data of the area where each fan is located, and randomly sampling according to the data set by taking the first preset duration plus the second preset duration as a time sequence length to obtain an area wind speed prediction data set;
and training the wind speed prediction model by using the regional wind speed prediction data set to obtain a trained wind speed prediction model.
5. The method of claim 4, wherein training the wind speed prediction model using the regional wind speed prediction dataset results in a trained wind speed prediction model, comprising;
taking data in a first preset duration of the regional wind speed prediction data set as input, taking data in a second preset duration of the regional wind speed prediction data set as expected output, training the wind speed prediction model to obtain a trained wind speed prediction model, wherein the trained wind speed prediction model is input into wind speed field space-time sequence data in the first preset duration, and outputting a wind speed field space-time sequence prediction result in the second preset duration.
6. The method of claim 1, wherein calculating a sequence of control amounts for each fan for a second predetermined time period based on the wind speed field spatiotemporal sequence prediction results comprises:
obtaining an optimal rotating speed curve of each fan according to the wind speed field space-time sequence prediction result and the inherent optimal power curve of the fan;
initializing control quantity of each fan in a second preset time period, and constructing an objective function according to the optimal rotating speed curve and the control quantity in the second preset time period;
and optimizing the control quantity by adopting an optimization algorithm, and outputting the control quantity with the minimum objective function as an optimal control quantity to obtain a control quantity sequence of each fan within a second preset time length.
7. The method of claim 6, wherein the objective function is represented as:
wherein L represents an objective function, N represents the number of control moments within a second preset time period,
indicating the optimal rotation speed corresponding to the wind speed at each moment in the second preset time period，/>
And representing a response result corresponding to the control quantity at each moment in the second preset time.
8. A wind farm level MPPT prediction model control device, comprising:
the acquisition module is used for acquiring wind speed field space-time sequence data of a wind power field range with a first preset duration;
the prediction module is used for predicting by using a trained wind speed prediction model based on the wind speed field space-time sequence data to obtain a wind speed field space-time sequence prediction result of a second preset duration, wherein the second preset duration is adjacent to the first preset duration;
the control module is used for calculating a control quantity sequence in a second preset duration of each fan according to the wind speed field space-time sequence prediction result and controlling the rotating speed of the fan at the next moment according to the control quantity of the first control quantity in the control quantity sequence.
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 of any of claims 1-7 when executing the computer program.
10. A non-transitory computer readable storage medium, on which a computer program is stored, characterized in that the computer program, when executed by a processor, implements the method according to any of claims 1-7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211641354.5A CN116123028A (en) | 2022-12-20 | 2022-12-20 | Wind power plant level MPPT prediction model control method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211641354.5A CN116123028A (en) | 2022-12-20 | 2022-12-20 | Wind power plant level MPPT prediction model control method and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116123028A true CN116123028A (en) | 2023-05-16 |
Family
ID=86303677
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211641354.5A Pending CN116123028A (en) | 2022-12-20 | 2022-12-20 | Wind power plant level MPPT prediction model control method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116123028A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117592767A (en) * | 2024-01-19 | 2024-02-23 | 新立讯科技股份有限公司 | OPC-based new energy automobile factory information fusion method and system |
Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102434391A (en) * | 2011-12-27 | 2012-05-02 | 南京理工大学 | Improved MPPT (maximum power point tracking) control method based on initial rotation speed adjustment |
| CN102708305A (en) * | 2012-06-20 | 2012-10-03 | 天津工业大学 | Wind speed sequence predicting method based on Kalman filtering fusion |
| CN102725520A (en) * | 2009-12-21 | 2012-10-10 | 维斯塔斯风力系统集团公司 | A wind turbine having a control method and controller for performing predictive control of a wind turbine generator |
| CN102792542A (en) * | 2010-03-19 | 2012-11-21 | 株式会社东芝 | Device for prediction of electricity generation amount, method for same, and program for same |
| KR101370542B1 (en) * | 2013-02-07 | 2014-03-06 | 인하대학교 산학협력단 | Method for controling mppt using wind speed estimation of wind power generation system |
| CN105373858A (en) * | 2015-11-26 | 2016-03-02 | 湘潭大学 | Wind power plant active power optimization method based on wind speed time sequence decomposition |
| JP2016136004A (en) * | 2015-01-23 | 2016-07-28 | 中国電力株式会社 | Power generation amount prediction device, power generation amount prediction method and program |
| US20180223812A1 (en) * | 2017-02-07 | 2018-08-09 | International Business Machines Corporation | Reducing curtailment of wind power generation |
| CN108918905A (en) * | 2018-07-09 | 2018-11-30 | 新疆金风科技股份有限公司 | The prediction technique and device of wind power generating set wind speed |
| CN111120205A (en) * | 2019-12-30 | 2020-05-08 | 明阳智慧能源集团股份公司 | Wind power plant regionalization control method based on laser radar |
| CN111425347A (en) * | 2020-03-23 | 2020-07-17 | 南京理工大学 | Wind turbine generator maximum power point tracking control method based on torque gain coefficient optimization |
| CN113027674A (en) * | 2019-12-24 | 2021-06-25 | 北京金风科创风电设备有限公司 | Control method and device of wind generating set |
| JP2021114856A (en) * | 2020-01-20 | 2021-08-05 | 株式会社東芝 | Wind power output prediction method and prediction device |
| CN113822418A (en) * | 2021-09-24 | 2021-12-21 | 中节能风力发电股份有限公司 | Wind power plant power prediction method, system, device and storage medium |
| CN114707734A (en) * | 2022-04-12 | 2022-07-05 | 华润电力技术研究院有限公司 | Method, device and medium for predicting ultra-short-term wind power |
| CN115030866A (en) * | 2022-06-29 | 2022-09-09 | 华能集团技术创新中心有限公司 | Wind power plant group control system |
| CN115330032A (en) * | 2022-07-26 | 2022-11-11 | 广东电网有限责任公司 | Method, device, storage medium and equipment for predicting wind speed of offshore wind farm |
| CN115409291A (en) * | 2022-10-31 | 2022-11-29 | 山东大学 | Wind speed corrected wind power prediction method and system |
-
2022
- 2022-12-20 CN CN202211641354.5A patent/CN116123028A/en active Pending
Patent Citations (18)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102725520A (en) * | 2009-12-21 | 2012-10-10 | 维斯塔斯风力系统集团公司 | A wind turbine having a control method and controller for performing predictive control of a wind turbine generator |
| CN102792542A (en) * | 2010-03-19 | 2012-11-21 | 株式会社东芝 | Device for prediction of electricity generation amount, method for same, and program for same |
| CN102434391A (en) * | 2011-12-27 | 2012-05-02 | 南京理工大学 | Improved MPPT (maximum power point tracking) control method based on initial rotation speed adjustment |
| CN102708305A (en) * | 2012-06-20 | 2012-10-03 | 天津工业大学 | Wind speed sequence predicting method based on Kalman filtering fusion |
| KR101370542B1 (en) * | 2013-02-07 | 2014-03-06 | 인하대학교 산학협력단 | Method for controling mppt using wind speed estimation of wind power generation system |
| JP2016136004A (en) * | 2015-01-23 | 2016-07-28 | 中国電力株式会社 | Power generation amount prediction device, power generation amount prediction method and program |
| CN105373858A (en) * | 2015-11-26 | 2016-03-02 | 湘潭大学 | Wind power plant active power optimization method based on wind speed time sequence decomposition |
| US20180223812A1 (en) * | 2017-02-07 | 2018-08-09 | International Business Machines Corporation | Reducing curtailment of wind power generation |
| CN108918905A (en) * | 2018-07-09 | 2018-11-30 | 新疆金风科技股份有限公司 | The prediction technique and device of wind power generating set wind speed |
| CN113027674A (en) * | 2019-12-24 | 2021-06-25 | 北京金风科创风电设备有限公司 | Control method and device of wind generating set |
| CN111120205A (en) * | 2019-12-30 | 2020-05-08 | 明阳智慧能源集团股份公司 | Wind power plant regionalization control method based on laser radar |
| JP2021114856A (en) * | 2020-01-20 | 2021-08-05 | 株式会社東芝 | Wind power output prediction method and prediction device |
| CN111425347A (en) * | 2020-03-23 | 2020-07-17 | 南京理工大学 | Wind turbine generator maximum power point tracking control method based on torque gain coefficient optimization |
| CN113822418A (en) * | 2021-09-24 | 2021-12-21 | 中节能风力发电股份有限公司 | Wind power plant power prediction method, system, device and storage medium |
| CN114707734A (en) * | 2022-04-12 | 2022-07-05 | 华润电力技术研究院有限公司 | Method, device and medium for predicting ultra-short-term wind power |
| CN115030866A (en) * | 2022-06-29 | 2022-09-09 | 华能集团技术创新中心有限公司 | Wind power plant group control system |
| CN115330032A (en) * | 2022-07-26 | 2022-11-11 | 广东电网有限责任公司 | Method, device, storage medium and equipment for predicting wind speed of offshore wind farm |
| CN115409291A (en) * | 2022-10-31 | 2022-11-29 | 山东大学 | Wind speed corrected wind power prediction method and system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117592767A (en) * | 2024-01-19 | 2024-02-23 | 新立讯科技股份有限公司 | OPC-based new energy automobile factory information fusion method and system |
| CN117592767B (en) * | 2024-01-19 | 2024-04-05 | 新立讯科技股份有限公司 | OPC-based new energy automobile factory information fusion method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Song et al. | Maximum power extraction for wind turbines through a novel yaw control solution using predicted wind directions | |
| EP3263889B1 (en) | System and method for assessing farm-level performance of a wind farm | |
| CN102434391B (en) | Improved MPPT (maximum power point tracking) control method based on initial rotation speed adjustment | |
| CN109312714B (en) | Control of a wind turbine taking noise into account | |
| CN104454346B (en) | Maximum power tracking control method for small permanent-magnet direct-drive wind power generation system | |
| Stanfel et al. | Proof-of-concept of a reinforcement learning framework for wind farm energy capture maximization in time-varying wind | |
| CN107045574B (en) | SVR-based effective wind speed estimation method for low wind speed section of wind generating set | |
| CN116123028A (en) | Wind power plant level MPPT prediction model control method and device | |
| CN104564520A (en) | System for automatic power estimation adjustment | |
| CN115333168A (en) | Offshore wind farm field level control strategy based on distributed rolling optimization | |
| EP2541052B1 (en) | Controlling a wind turbine using a neural network function | |
| CN107313898B (en) | The method of wind generator system control based on Markov jump rule | |
| CN113759708B (en) | Optimization control method and device of system and electronic equipment | |
| CN113027674B (en) | Control method and device of wind generating set | |
| CN117669968A (en) | Wind farm scheduling method, device, equipment and medium | |
| CN113947007A (en) | Energy load prediction method, device and equipment | |
| CN117052596A (en) | Fan yaw control method and system based on deep reinforcement learning | |
| CN111379671B (en) | Method and device for determining turbulence intensity | |
| Chen et al. | Reward adaptive wind power tracking control based on deep deterministic policy gradient | |
| CN113202691B (en) | Wind power generation assembly control method, device, equipment and medium | |
| CN116085191A (en) | Combined prediction control method and device for pitch angle of wind power generator of wind power plant | |
| CN116044654A (en) | Control method and equipment for single-machine pitch angle prediction model of wind driven generator | |
| CN113027675A (en) | Control method and control device for wind power plant and wind generating set | |
| Moussa et al. | Wind turbine emulator controlled through field programmable gate array: modeling, analysis, and design | |
| CN116292097B (en) | Fan set control method and system based on intelligent perception of laser radar |
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 |