CN115935811A - Distributed wind turbine generator power prediction method based on mathematical model - Google Patents
Distributed wind turbine generator power prediction method based on mathematical model Download PDFInfo
- Publication number
- CN115935811A CN115935811A CN202211499104.2A CN202211499104A CN115935811A CN 115935811 A CN115935811 A CN 115935811A CN 202211499104 A CN202211499104 A CN 202211499104A CN 115935811 A CN115935811 A CN 115935811A
- Authority
- CN
- China
- Prior art keywords
- wind turbine
- turbine generator
- data
- distributed wind
- mathematical model
- 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
- 238000013178 mathematical model Methods 0.000 title claims abstract description 69
- 238000000034 method Methods 0.000 title claims abstract description 49
- 239000002245 particle Substances 0.000 claims abstract description 62
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 53
- 238000012549 training Methods 0.000 claims abstract description 16
- 238000004364 calculation method Methods 0.000 claims description 18
- 230000006870 function Effects 0.000 claims description 17
- 238000003860 storage Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 238000012544 monitoring process Methods 0.000 claims description 6
- 210000002569 neuron Anatomy 0.000 claims description 6
- 238000005457 optimization Methods 0.000 claims description 6
- 238000005070 sampling Methods 0.000 claims description 6
- 238000006467 substitution reaction Methods 0.000 claims description 4
- 238000001556 precipitation Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 abstract description 3
- 230000008878 coupling Effects 0.000 abstract description 2
- 238000010168 coupling process Methods 0.000 abstract description 2
- 238000005859 coupling reaction Methods 0.000 abstract description 2
- 230000007246 mechanism Effects 0.000 abstract description 2
- 238000000605 extraction Methods 0.000 description 3
- 238000013507 mapping Methods 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 230000006978 adaptation Effects 0.000 description 2
- 238000010276 construction Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 230000001902 propagating effect Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000005293 physical law Methods 0.000 description 1
- 238000010248 power generation Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- 238000009827 uniform distribution Methods 0.000 description 1
- 238000012795 verification Methods 0.000 description 1
Images
Classifications
-
- 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
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Control Of Eletrric Generators (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses a distributed wind turbine generator power prediction method based on a mathematical model, which comprises the following steps: acquiring historical data and meteorological data of the distributed wind turbine generator, and establishing a mathematical model of the distributed wind turbine generator; setting an initialization parameter of a particle swarm heuristic algorithm, and setting a fitness function; optimizing the model through historical power data and a particle swarm heuristic algorithm, and acquiring optimal parameters; training and predicting input data of a mathematical model of the distributed wind turbine generator by using a WOA-CNN-LSTM algorithm, and inputting a prediction result into the model to predict the power of the distributed wind turbine generator; the method combines the mathematical model and the artificial intelligence algorithm, overcomes the problem of insufficient prediction precision caused by the fact that the artificial intelligence algorithm cannot fully reflect the operation mechanism of the distributed wind turbine generator, and meanwhile links the electrical data and the weather data of the distributed wind turbine generator to perform coupling prediction, so that the accuracy of power prediction of the distributed wind turbine generator is improved.
Description
Technical Field
The invention relates to the technical field of wind turbine generator power prediction, in particular to a distributed wind turbine generator power prediction method based on a mathematical model.
Background
In recent years, the proportion of wind power in an electric power system is continuously increased, and a wind turbine plays an increasingly important role in the electric power system, so that the power prediction of the wind turbine becomes more important under the background, the power prediction of a distributed wind turbine is performed, the reasonable scheduling and the economic operation of a power generation plan of the electric power system are facilitated, and the safe and stable operation of the electric power system is ensured.
The traditional single wind power prediction algorithm has certain defects; the single wind power physical prediction model parameter is difficult to determine, and the physical model is difficult to construct; a single data driving algorithm ignores the physical law, has strong dependence on data and has an error mapping condition; the traditional single wind power prediction algorithm is difficult to adapt to complex and various wind power data and meteorological data, and the wind power prediction precision is insufficient.
Therefore, how to accurately construct a wind power physical prediction model and establish an accurate wind power prediction method becomes a technical problem to be solved urgently.
Disclosure of Invention
This section is for the purpose of summarizing some aspects of embodiments of the invention and to briefly introduce some preferred embodiments. In this section, as well as in the abstract and the title of the invention of this application, simplifications or omissions may be made to avoid obscuring the purpose of the section, the abstract and the title, and such simplifications or omissions are not intended to limit the scope of the invention.
The present invention has been made in view of the above-mentioned problems.
In a first aspect of the embodiments of the present invention, a method for predicting power of a distributed wind turbine generator based on a mathematical model is provided, including: acquiring historical data and meteorological data of the distributed wind turbine generator, and establishing a mathematical model of the distributed wind turbine generator based on the historical data and the meteorological data; setting initialization parameters of a particle swarm heuristic algorithm, and setting a target function of the particle swarm heuristic algorithm; performing optimization calculation on the mathematical model of the distributed wind turbine generator through historical power data of the distributed wind turbine generator and the particle swarm heuristic algorithm, and acquiring optimal parameters; and training and predicting the input data of the mathematical model of the distributed wind turbine generator by using a WOA-CNN-LSTM algorithm, and inputting the prediction result into the mathematical model of the distributed wind turbine generator to predict the power of the distributed wind turbine generator.
As a preferred scheme of the distributed wind turbine generator power prediction method based on the mathematical model, the method comprises the following steps: the acquisition of historical data and meteorological data of the distributed wind turbines comprises,
the type of the acquired data comprises basic data, dynamic data and meteorological data;
the basic data comprise equipment nameplate parameters, equipment standing accounts and experimental data before equipment operation;
the dynamic data comprises equipment online monitoring data, equipment operation data and charged monitoring data;
the meteorological data comprise wind direction data, wind speed data, temperature data, humidity data, air pressure data and precipitation data.
As a preferred scheme of the distributed wind turbine generator power prediction method based on the mathematical model, the method comprises the following steps: the calculation of the mathematical model of the distributed wind turbine comprises,
wherein, P r Representing active power of the stator of the generator, u dr Representing stator d-axis voltage, i dr Represents stator d-axis current, u qr Representing stator q-axis voltage, i qr Denotes stator q-axis current, s denotes slip, i qs Representing rotor q-axis current, L m Representing mutual inductance u qs Representing rotor q-axis voltage, R s Represents the rotor resistance, i ds Representing rotor d-axis current, L s Representing stator inductance, R r Represents the stator resistance u ds Representing rotor d-axis voltage, L r Representing the rotor inductance.
As a preferred scheme of the distributed wind turbine generator power prediction method based on the mathematical model, the method comprises the following steps: the setting of the objective function of the particle swarm heuristic comprises,
the particle swarm heuristic algorithm is used for carrying out optimization calculation by taking the square sum minimum value of the deviation of the active power of the stator output by the distributed wind turbine generator as a target function;
the calculation of the objective function f includes,
where m represents the number of power data samples, P ri The active power value P of the stator, which is obtained by calculating the ith sampling point data through a mathematical model of the distributed wind turbine generator system Gri Representing stator active measured at ith sampling pointThe power value.
As a preferred scheme of the distributed wind turbine generator power prediction method based on the mathematical model, the method comprises the following steps: the obtaining of the optimal parameters may include,
initializing the position and the speed of the particles into random numbers in a D-dimensional search space, and evaluating the position of each particle by using a fitness function;
comparing the fitness value with the individual optimal value of the particle and updating the individual optimal value, comparing the fitness value of the particle with the global optimal value, and updating the global optimal value to be the optimal value of the two;
and updating the positions of the particles, and circulating the steps until the fitness value is optimal or the maximum number of generations is reached.
As a preferred scheme of the mathematical model-based power prediction method for the distributed wind turbine generator, the method comprises the following steps: the calculation of the updated particle position includes,
wherein,
indicates the speed of the i-th particle during the (k + 1) -th generation, is selected>
Representing the velocity of the ith particle during the kth generation, w representing the inertial weight coefficient, c 1 Represents a learning factor, r 1 Denotes a uniform distribution between (0, 1)Random number of (2), P best Represents the individual optimum of the particle>
Indicates the position of the i-th particle during the kth generation>
Represents the position of the ith particle in the (k + 1) th substitution process, c 2 Represents a learning factor, r 2 Represents a random number, g, uniformly distributed between (0, 1) best Represents a global optimum, w start Representing the initial inertial weight, w end Representing the terminating inertial weight, t max Indicating the maximum update time and t the update time.
As a preferred scheme of the distributed wind turbine generator power prediction method based on the mathematical model, the method comprises the following steps: the training and predicting the input data of the mathematical model of the distributed wind turbine generator comprises the following steps,
respectively optimizing the convolution kernel size and the kernel number of the CNN first convolution layer and the CNN second convolution layer, the LSTM neuron number and the learning rate and the neurons of the full connection layer by using a WOA algorithm;
extracting characteristic information of meteorological information data of the input layer through CNN, and inputting the characteristic information output by the second convolution layer into LSTM for training;
and constructing a prediction model based on the training result, and outputting the result through the full-chain layer.
In a second aspect of the embodiments of the present invention, a mathematical model-based power prediction system for a distributed wind turbine generator is provided, including:
the model establishing module is used for acquiring historical data and meteorological data of the distributed wind turbine generator and establishing a mathematical model of the distributed wind turbine generator based on the historical data and the meteorological data;
the parameter optimizing module is used for setting initialization parameters of a particle swarm heuristic algorithm, setting a target function of the particle swarm heuristic algorithm, performing optimizing calculation on a mathematical model of the distributed wind turbine generator through historical power data of the distributed wind turbine generator and the particle swarm heuristic algorithm, and acquiring optimal parameters;
and the power prediction module is used for training and predicting the input data of the distributed wind turbine generator mathematical model by using a WOA-CNN-LSTM algorithm, and inputting the prediction result into the distributed wind turbine generator mathematical model to predict the power of the distributed wind turbine generator.
In a third aspect of embodiments of the present invention, there is provided an apparatus, comprising,
a processor;
a memory for storing processor-executable instructions;
the processor is configured to invoke the instructions stored by the memory to perform the method of any embodiment of the invention.
In a fourth aspect of the embodiments of the present invention, there is provided a computer-readable storage medium having stored thereon computer program instructions, including:
which when executed by a processor implement the method according to any of the embodiments of the invention.
The invention has the beneficial effects that: the invention provides a mathematical model-based power prediction method for a distributed wind turbine generator, which adopts a particle swarm heuristic algorithm to accurately solve the mathematical model of the distributed wind turbine generator and solves the problems of difficult construction of a physical model of the distributed wind turbine generator and inaccurate parameter setting; the invention provides a feasible mathematical model and data-driven distributed wind turbine generator power prediction method, and solves the problems of wrong mapping and insufficient accuracy of the traditional single wind turbine generator power prediction method; in addition, the optimal hyper-parameter combination in the CNN-LSTM model is solved by adopting a WOA algorithm, the CNN characteristic information extraction capability is enhanced, the optimal LSTM parameter is solved, the LSTM learning capability is generalized, and the model adaptation capability to complex weather information and unit state parameters is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the drawings needed to be used in the description of the embodiments will be briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise. Wherein:
FIG. 1 is an overall flow chart of a mathematical model-based distributed wind turbine power prediction method provided by the invention;
FIG. 2 is a flow chart of a WOA-CNN-LSTM algorithm in the mathematical model-based power prediction method for the distributed wind turbine generator.
Detailed Description
In order to make the aforementioned objects, features and advantages of the present invention more comprehensible, embodiments accompanying figures of the present invention are described in detail below, and it is apparent that the described embodiments are a part, not all or all of the embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without making creative efforts based on the embodiments of the present invention, shall fall within the protection scope of the present invention.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present invention, however, the present invention may be practiced otherwise than as specifically described herein, and it will be appreciated by those skilled in the art that the present invention may be practiced without departing from the spirit and scope of the present invention and that the present invention is not limited by the specific embodiments disclosed below.
Furthermore, reference herein to "one embodiment" or "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one implementation of the invention. The appearances of the phrase "in one embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are separate or alternative embodiments mutually exclusive of other embodiments.
The present invention will be described in detail with reference to the drawings, wherein the cross-sectional views illustrating the structure of the device are not enlarged partially in general scale for convenience of illustration, and the drawings are only exemplary and should not be construed as limiting the scope of the present invention. In addition, the three-dimensional dimensions of length, width and depth should be included in the actual fabrication.
Meanwhile, in the description of the present invention, it should be noted that the terms "upper, lower, inner and outer" and the like indicate orientations or positional relationships based on the orientations or positional relationships shown in the drawings, and are only for convenience of describing the present invention and simplifying the description, but do not indicate or imply that the referred device or element must have a specific orientation, be constructed in a specific orientation and operate, and thus, cannot be construed as limiting the present invention. Furthermore, the terms first, second, or third are used for descriptive purposes only and are not to be construed as indicating or implying relative importance.
The terms "mounted, connected and connected" in the present invention are to be understood broadly, unless otherwise explicitly specified or limited, for example: can be fixedly connected, detachably connected or integrally connected; they may be mechanically, electrically, or directly connected, or indirectly connected through intervening media, or may be interconnected between two elements. The specific meanings of the above terms in the present invention can be understood in a specific case to those of ordinary skill in the art.
Example 1
Referring to fig. 1 to 2, an embodiment of the present invention provides a method for predicting power of a distributed wind turbine generator based on a mathematical model, including:
s1: historical data and meteorological data of the distributed wind turbine generator are obtained, and a mathematical model of the distributed wind turbine generator is established based on the historical data and the meteorological data. It should be noted that:
the acquired data sources are asset management units and production operation units of the distributed wind turbine generator, and the types of the acquired data comprise basic data, dynamic data and meteorological data;
it should be noted that the basic data includes equipment nameplate parameters, equipment ledgers and experimental data before equipment commissioning, the dynamic data includes equipment online monitoring data, equipment operation data and electrified monitoring data, and the meteorological data includes wind direction data, wind speed data, temperature data, humidity data, air pressure data and precipitation data;
further, the calculation of the mathematical model of the distributed wind turbine generator comprises,
wherein, P r Representing active power of the stator of the generator, u dr Representing stator d-axis voltage, i dr Representing stator d-axis current, u qr Representing stator q-axis voltage, i qr Representing stator q-axis current, s slip, i qs Representing rotor q-axis current, L m Representing mutual inductance u qs Representing rotor q-axis voltage, R s Representing the rotor resistance, i ds Representing rotor d-axis current, L s Representing stator inductance, R r Represents the stator resistance u ds Representing the rotor d-axis voltage, L r Representing the rotor inductance.
S2: setting initialization parameters of the particle swarm heuristic algorithm, and setting a target function of the particle swarm heuristic algorithm. It should be noted that:
the particle swarm heuristic algorithm is used for carrying out optimization calculation by taking the square sum minimum value of the deviation of the active power of the output stator of the distributed wind turbine generator as a target function, the calculation of the target function f comprises,
where m represents the number of power data samples, P ri The active power value P of the stator, which is obtained by calculating the ith sampling point data through a mathematical model of the distributed wind turbine generator system Gri And the value of the active power of the stator measured by the ith sampling point is represented.
S3: and performing optimization calculation on the mathematical model of the distributed wind turbine generator through historical power data of the distributed wind turbine generator and a particle swarm heuristic algorithm, and acquiring optimal parameters. It should be noted that:
the step of solving the mathematical model parameters of the distributed wind turbine generator set by the particle swarm heuristic algorithm comprises the following steps:
(1) initializing parameters: initializing the position and velocity of the particle to a random number in a D-dimensional search space;
(2) evaluation of the position of the particles: evaluating the position of each particle by using a fitness function;
(3) comparing individuals;
it should be noted that, in the first step, the fitness value and the individual optimal value of the particle are compared and the individual optimal value is updated, and in the second step, the fitness value and the global optimal value of the particle are compared and the global optimal value is updated to the optimal value of the two;
(4) updating the position of the particle;
it should be noted that the calculation of updating the position and orientation of the particles includes,
wherein,
indicates the speed of the ith particle during the (k + 1) th passage, is->
Representing the velocity of the ith particle during the kth generation, w representing the inertial weight coefficient, c 1 Represents a learning factor, r 1 Represents a random number, P, uniformly distributed between (0, 1) best Represents the individual optimum of the particle,. Sup.>
Indicates the position of the ith particle in the kth generation process，
Represents the position of the ith particle in the (k + 1) th substitution process, c 2 Represents a learning factor, r 2 Random numbers, g, which are uniformly distributed between (0, 1) best Represents a global optimum, w start Representing the initial inertial weight, w end Representing the terminating inertial weight, t max Represents the maximum update time, and t represents the update time;
(5) and (5) finishing the generation selection: and the steps are circulated until the fitness value is optimal or the maximum number of generations is reached.
S4: and training and predicting input data of the mathematical model of the distributed wind turbine generator by using a WOA-CNN-LSTM algorithm, and inputting a prediction result into the mathematical model of the distributed wind turbine generator to predict the power of the distributed wind turbine generator. It should be noted that:
the method for training and predicting the input data of the mathematical model of the distributed wind turbine generator comprises the following steps:
respectively optimizing the convolution kernel size and the kernel number of the CNN first convolution layer and the CNN second convolution layer, the LSTM neuron number and the learning rate and the neurons of the full connection layer by using a WOA algorithm;
performing characteristic information extraction on meteorological information data of the input layer through the CNN, and inputting characteristic information output by the second convolutional layer into the LSTM for training;
constructing a prediction model based on the training result, and outputting the result through a full-link layer;
and further, inputting the prediction result into a mathematical model of the distributed wind turbine generator to predict the power of the distributed wind turbine generator.
It should be noted that the invention provides a mathematical model-based distributed wind turbine generator power prediction method, which adopts a particle swarm heuristic algorithm to accurately solve the mathematical model of the distributed wind turbine generator, and solves the problems of difficult construction of the physical model of the distributed wind turbine generator and inaccurate parameter setting; the invention provides a feasible mathematical model and data-driven distributed wind turbine generator power prediction method, and solves the problems of wrong mapping and insufficient accuracy of the traditional single wind turbine generator power prediction method; in addition, the optimal hyper-parameter combination in the CNN-LSTM model is solved by adopting a WOA algorithm, the CNN characteristic information extraction capability is enhanced, the optimal LSTM parameter is solved, the LSTM learning capability is generalized, and the model adaptation capability to complex weather information and unit state parameters is improved.
In a second aspect of the present disclosure,
the utility model provides a distributed wind turbine generator system power prediction system based on mathematical model, includes:
the model establishing module is used for acquiring historical data and meteorological data of the distributed wind turbine generator and establishing a mathematical model of the distributed wind turbine generator based on the historical data and the meteorological data;
the parameter optimizing module is used for setting initialization parameters of the particle swarm heuristic algorithm, setting a target function of the particle swarm heuristic algorithm, performing optimizing calculation on a mathematical model of the distributed wind turbine generator through historical power data of the distributed wind turbine generator and the particle swarm heuristic algorithm, and acquiring optimal parameters;
and the power prediction module is used for training and predicting the input data of the mathematical model of the distributed wind turbine generator by using a WOA-CNN-LSTM algorithm and inputting the prediction result into the mathematical model of the distributed wind turbine generator to predict the power of the distributed wind turbine generator.
In a third aspect of the present disclosure,
providing an apparatus comprising:
a processor;
a memory for storing processor-executable instructions;
wherein the processor is configured to invoke the memory-stored instructions to perform the method of any of the preceding.
In a fourth aspect of the present disclosure,
there is provided a computer readable storage medium having computer program instructions stored thereon, comprising:
the computer program instructions, when executed by a processor, implement the method of any of the preceding.
The present invention may be methods, apparatus, systems, and/or computer program products that may include a computer-readable storage medium having computer-readable program instructions embodied therewith for performing various aspects of the present invention.
The computer readable storage medium may be a tangible device that can hold and store the instructions for use by the instruction execution device. The computer readable storage medium may be, for example, but not limited to, an electronic memory device, a magnetic memory device, an optical memory device, an electromagnetic memory device, a semiconductor memory device, or any suitable combination of the foregoing. More specific examples (a non-exhaustive list) of the computer readable storage medium would include the following: a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), a Static Random Access Memory (SRAM), a portable compact disc read-only memory (CD-ROM), a Digital Versatile Disc (DVD), a memory stick, a floppy disk, a mechanical coding device, such as punch cards or in-groove projection structures having instructions stored thereon, and any suitable combination of the foregoing. Computer-readable storage media as used herein is not to be interpreted as a transitory signal per se, such as a radio wave or other freely propagating electromagnetic wave, an electromagnetic wave propagating through a waveguide or other transmission medium (e.g., optical pulses through a fiber optic cable), or an electrical signal transmitted through an electrical wire.
Example 2
Different from the first embodiment, the embodiment provides a verification test of the distributed wind turbine generator power prediction method based on the mathematical model, and aims to verify and explain the technical effects adopted in the method.
In the embodiment, the LSTM algorithm, the CNN-LSTM algorithm, the WOA-LSTM algorithm and the WOA-CNN-LSTM algorithm used herein are used for setting the same prediction step length to perform independent iterative operation to perform distributed wind turbine generator power prediction under the same data sequence, and the RMSE value and the R value obtained after convergence of each model are used for prediction of the distributed wind turbine generator power 2 The values were compared as shown in table 1;
table 1: and comparing the power prediction results of different algorithms.
| Algorithm | RMSE(MW) | R 2 |
| LSTM | 10.641 | 0.912 |
| CNN-LSTM | 6.833 | 0.939 |
| WOA-LSTM | 5.531 | 0.963 |
| WOA-CNN-LSTM (invention) | 4.627 | 0.971 |
As can be seen from Table 1, the WOA-CNN-LSTM algorithm has higher precision compared with other three algorithms and can better map the relation between weather and unit parameters according to the prediction results of the same prediction step length under the same data sequence; therefore, the method provided by the invention can make up for the problem of insufficient prediction precision caused by the fact that an artificial intelligence algorithm cannot fully reflect the operation mechanism of the distributed wind turbine generator, and meanwhile, the electrical data and the weather data of the distributed wind turbine generator are linked for coupling prediction, so that the accuracy of power prediction of the distributed wind turbine generator is improved.
It should be noted that the above-mentioned embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention is described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.
Claims (10)
1. A distributed wind turbine generator power prediction method based on a mathematical model is characterized by comprising the following steps:
acquiring historical data and meteorological data of the distributed wind turbine generator, and establishing a mathematical model of the distributed wind turbine generator based on the historical data and the meteorological data;
setting initialization parameters of a particle swarm heuristic algorithm, and setting a target function of the particle swarm heuristic algorithm;
performing optimization calculation on the mathematical model of the distributed wind turbine generator through historical power data of the distributed wind turbine generator and the particle swarm heuristic algorithm, and acquiring optimal parameters;
and training and predicting the input data of the mathematical model of the distributed wind turbine generator by using a WOA-CNN-LSTM algorithm, and inputting the prediction result into the mathematical model of the distributed wind turbine generator to predict the power of the distributed wind turbine generator.
2. The mathematical model-based distributed wind turbine generator power prediction method of claim 1, characterized in that: the acquisition of the historical data and the meteorological data of the distributed wind generation sets comprises,
the type of the acquired data comprises basic data, dynamic data and meteorological data;
the basic data comprise equipment nameplate parameters, equipment standing accounts and experimental data before equipment operation;
the dynamic data comprises equipment online monitoring data, equipment operation data and charged monitoring data;
the meteorological data comprise wind direction data, wind speed data, temperature data, humidity data, air pressure data and precipitation data.
3. The mathematical model-based distributed wind turbine generator power prediction method of claim 2, wherein: the calculation of the mathematical model of the distributed wind turbine generator comprises,
wherein, P r Representing active power of the generator stator, u dr Representing stator d-axis voltage, i dr Representing stator d-axis current, u qr Representing stator q-axis voltage, i qr Denotes stator q-axis current, s denotes slip, i qs Representing rotor q-axis current, L m Representing mutual inductance u qs Representing rotor q-axis voltage, R s Representing the rotor resistance, i ds Representing rotor d-axis current, L s Representing stator inductance, R r Represents the stator resistance u ds Representing rotor d-axis voltage, L r Representing the rotor inductance.
4. The mathematical model-based distributed wind turbine generator power prediction method of claim 3, wherein: the setting of the objective function of the particle swarm heuristic comprises,
the particle swarm heuristic algorithm is used for carrying out optimization calculation by taking the square sum minimum value of the deviation of the active power of the stator output by the distributed wind turbine generator as a target function;
the calculation of the objective function f includes,
where m represents the number of power data samples, P ri Represents the stator active power value P calculated by the ith sampling point data through a mathematical model of the distributed wind turbine generator Gri Represents the ithAnd measuring the active power value of the stator by a sampling point.
5. The mathematical model-based distributed wind turbine generator power prediction method of any of claims 1 to 4, characterized in that: the obtaining of the optimal parameters may include,
initializing the position and the speed of the particles into random numbers in a D-dimensional search space, and evaluating the position of each particle by using a fitness function;
comparing the fitness value with the individual optimal value of the particle and updating the individual optimal value, comparing the fitness value of the particle with the global optimal value, and updating the global optimal value to be the optimal value of the two;
and updating the positions of the particles, and circulating the steps until the fitness value is optimal or the maximum number of generations is reached.
6. The mathematical model-based distributed wind turbine generator power prediction method of claim 5, wherein: the calculation of the updated particle position includes,
wherein,
indicates the speed of the i-th particle during the (k + 1) -th generation, is selected>
Representing the velocity of the ith particle during the kth generation, w representing the inertial weight coefficient, c 1 Represents a learning factor, r 1 Represents a random number, P, uniformly distributed between (0, 1) best Represents the individual optimum of the particle>
Indicates the position of the ith particle during the kth generation, and>
denotes the position of the ith particle in the k +1 th substitution, c 2 Represents a learning factor, r 2 Random numbers, g, which are uniformly distributed between (0, 1) best Represents a global optimum, w start Representing the initial inertial weight, w end Representing the terminating inertial weight, t max Representing the maximum update time and t representing the update time.
7. The mathematical model-based distributed wind turbine generator power prediction method of claim 6, characterized in that: the training and predicting the input data of the mathematical model of the distributed wind turbine generator comprises the following steps,
respectively optimizing the convolution kernel size and the kernel number of the CNN first convolution layer and the CNN second convolution layer, the LSTM neuron number and the learning rate and the neurons of the full connection layer by using a WOA algorithm;
extracting characteristic information of meteorological information data of the input layer through CNN, and inputting the characteristic information output by the second convolution layer into LSTM for training;
and constructing a prediction model based on the training result, and outputting the result through the full-link layer.
8. A distributed wind turbine generator system power prediction system based on a mathematical model is characterized by comprising:
the model building module is used for obtaining historical data and meteorological data of the distributed wind turbine generator and building a mathematical model of the distributed wind turbine generator based on the historical data and the meteorological data;
the parameter optimizing module is used for setting initialization parameters of a particle swarm heuristic algorithm, setting a target function of the particle swarm heuristic algorithm, performing optimizing calculation on a mathematical model of the distributed wind turbine generator through historical power data of the distributed wind turbine generator and the particle swarm heuristic algorithm, and acquiring optimal parameters;
and the power prediction module is used for training and predicting the input data of the mathematical model of the distributed wind turbine generator by using a WOA-CNN-LSTM algorithm, and inputting the prediction result into the mathematical model of the distributed wind turbine generator to predict the power of the distributed wind turbine generator.
9. An apparatus, characterized in that the apparatus comprises,
a processor;
a memory for storing processor-executable instructions;
the processor is configured to invoke the memory-stored instructions to perform the method of any of claims 1-7.
10. A computer readable storage medium having computer program instructions stored thereon, wherein the computer program instructions, when executed by a processor, implement the method of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211499104.2A CN115935811A (en) | 2022-11-28 | 2022-11-28 | Distributed wind turbine generator power prediction method based on mathematical model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211499104.2A CN115935811A (en) | 2022-11-28 | 2022-11-28 | Distributed wind turbine generator power prediction method based on mathematical model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115935811A true CN115935811A (en) | 2023-04-07 |
Family
ID=86655268
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211499104.2A Pending CN115935811A (en) | 2022-11-28 | 2022-11-28 | Distributed wind turbine generator power prediction method based on mathematical model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115935811A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116955966A (en) * | 2023-09-20 | 2023-10-27 | 山东科技大学 | Method for judging water-rich grade of mine roof |
| CN118336916A (en) * | 2024-04-12 | 2024-07-12 | 威海凯瑞电气股份有限公司 | ABCLINK electric comprehensive monitoring system |
-
2022
- 2022-11-28 CN CN202211499104.2A patent/CN115935811A/en active Pending
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116955966A (en) * | 2023-09-20 | 2023-10-27 | 山东科技大学 | Method for judging water-rich grade of mine roof |
| CN116955966B (en) * | 2023-09-20 | 2023-12-19 | 山东科技大学 | Method for judging water-rich grade of mine roof |
| CN118336916A (en) * | 2024-04-12 | 2024-07-12 | 威海凯瑞电气股份有限公司 | ABCLINK electric comprehensive monitoring system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN115935811A (en) | Distributed wind turbine generator power prediction method based on mathematical model | |
| CN101661530B (en) | Method for acquiring steady-state equivalent wind speed and generated power in wind power station based on correlation analysis | |
| CN106875037B (en) | Wind power prediction method and device | |
| CN111753893A (en) | Wind turbine generator power cluster prediction method based on clustering and deep learning | |
| CN110119570A (en) | A kind of farm model parameters validation method of measured data driving | |
| CN116028822B (en) | Electric energy meter error state evaluation method, system, equipment and storage medium | |
| CN116485049B (en) | Electric energy metering error prediction and optimization system based on artificial intelligence | |
| CN113821931B (en) | Fan output power prediction method and system | |
| CN107634516A (en) | A kind of distribution method for estimating state based on Grey Markov Chain | |
| CN116707331B (en) | Inverter output voltage high-precision adjusting method and system based on model prediction | |
| CN115908051A (en) | Method for determining energy storage capacity of power system | |
| CN103632314B (en) | Wind energy turbine set generalized node feature modeling method based on probability statistics | |
| CN115659844B (en) | Simulation method and device based on wind power plant dynamic model and computer equipment | |
| CN102539823A (en) | Method for forecasting wind speed distribution of WTG (wind turbine generator) | |
| CN116777109A (en) | Wind generating set equipment state evaluation method and system | |
| CN111612648A (en) | Training method and device of photovoltaic power generation prediction model and computer equipment | |
| CN116680567A (en) | Missing state variable filling method and device for wind driven generator | |
| CN114221334B (en) | Rapid state estimation method based on graph neural network | |
| CN116663889A (en) | Novel power system risk assessment method based on improved Gaussian model | |
| CN116307139A (en) | Wind power ultra-short-term prediction method for optimizing and improving extreme learning machine | |
| CN112581311B (en) | Method and system for predicting long-term output fluctuation characteristics of aggregated multiple wind power plants | |
| CN112231979B (en) | Mountain area instantaneous wind condition forecasting method based on computational fluid dynamics and machine learning | |
| CN114233580A (en) | Method and device for correcting wind speed of cabin of wind turbine generator | |
| CN113988414A (en) | Wind power output power prediction method based on P _ LSTNet and weighted Markov verification | |
| CN116937538A (en) | ARIMA-BP-LSTM multi-feature fusion-based ultra-short-term wind power prediction method and device |
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 |