CN115829140B - Wind power generation plant power generation amount prediction method and system based on machine learning - Google Patents
Wind power generation plant power generation amount prediction method and system based on machine learning Download PDFInfo
- Publication number
- CN115829140B CN115829140B CN202211607591.XA CN202211607591A CN115829140B CN 115829140 B CN115829140 B CN 115829140B CN 202211607591 A CN202211607591 A CN 202211607591A CN 115829140 B CN115829140 B CN 115829140B
- Authority
- CN
- China
- Prior art keywords
- wind
- wind speed
- power generation
- upstream
- electric field
- 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.)
- Active
Links
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
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A30/00—Adapting or protecting infrastructure or their operation
Abstract
The invention relates to the technical field of wind power generation, in particular to a wind power generation field generating capacity prediction method and system based on machine learning.
Description
Technical Field
The application relates to the technical field of wind power generation, in particular to a wind power generation field generating capacity prediction method and system based on machine learning.
Background
Energy is an important material foundation for social development, and different energy strategies are established in all countries of the world nowadays. Energy has become one of the core competitions between the various world nations. Energy safety is an indispensable part of national security. The energy structure in China mainly uses fossil fuel, such as various energy sources of coal, petroleum, natural gas, nuclear energy and the like. These energy sources, especially the most consumed reserves of coal and oil, are very limited. According to authoritative data, world petroleum can also be developed for 52.9 years, coal for 109 years and natural gas for 55.7 years. China is a large population country, and with the development of economy, china becomes an energy import large country, and the total energy consumption is increased year by year. The annual increase of fossil energy consumption brings very serious damage to the ecological environment, and the severe changes of acid rain, haze and global climate are all related to the large-scale development and consumption of fossil energy by human beings. The environment is the root of human survival, and economic development cannot be at the expense of the environment.
With the development of technology, the global energy consumption increases year by year, and the energy consumption of people in both developing and developed countries is continuously increasing. The traditional energy industry cannot meet the economic development, and the development of new energy industry is imperative. Along with the increase of energy consumption, the practical pressure of human development of renewable energy sources is increasing, and renewable energy sources such as solar energy, water energy, biomass energy and the like are rapidly developed.
Wind energy is considered one of the most potential renewable energy sources. Starting from 2005, the global wind power growth potential is rapid, the newly-increased installed capacity in 2015 reaches 63,013MW, the accumulated installed capacity reaches 432,419MW, and the annual growth rate of 22% is realized. Wind energy is divided into land wind energy and sea wind energy, and the development amount of the wind energy theory in China is very large, and 6 to 10 hundred million KW on land and 20 hundred million KW on sea are realized. Under the complex international energy pattern and severe ecological environment pressure, large-scale development and utilization of wind energy is a very scientific choice. Today, the total amount of wind power installations in China is already in the first place in the world.
The wind itself is indeterminate and uncontrollable. Although the site selection and factory establishment of wind power enterprises are all in areas where wind energy can be gathered, the wind power is continuously changed along with time. The continuous change of wind speed over time results in a continuous change of the output power of the wind generator over time. The early wind power output power of the wind power industry development has small duty ratio, the disturbance to the power grid is also very small, the power system carries out feedback adjustment on parameters such as voltage, frequency and the like in a scientific range through primary adjustment and secondary adjustment, and the influence of wind power fluctuation can be completely and automatically adjusted to be offset. With the continuous development of the wind power industry, the total wind power internet surfing amount is continuously increased, and the safety of a power grid is increasingly threatened. The flexibility of electric energy as an energy source that can be transmitted over long distances and its convenience is emphasized in the energy market. However, in the process of power long-distance transmission, the balance of supply and demand must be maintained, which is an important issue in the research of power systems. But as the scale of wind power increases, this difficulty becomes more difficult to solve. The volatility of wind power itself has become a major impediment to the development of the wind power industry. Wind power enterprises must provide a more reliable source of energy to the grid, and therefore wind power must be predicted.
Disclosure of Invention
In order to solve the technical problems, the application provides a wind power generation plant generating capacity prediction method and system based on machine learning, and the prediction of a result of real-time generating capacity in a wind power generation plant is realized through a plurality of models.
In order to achieve the above purpose, the technical solution adopted in the embodiment of the present application is as follows:
in a first aspect, a method for predicting power generation capacity of a wind power plant based on machine learning is provided, including: acquiring real-time generated energy of a plurality of wind motors and a plurality of real-time wind speed information corresponding to the wind motors in a wind power plant under the same time, constructing a wind speed relation model corresponding to the wind motors based on the plurality of real-time wind speed information and standard real-time wind speed information, and correcting a motor joint model based on the real-time wind speed information and the wind speed relation model to obtain a target motor joint model, wherein the motor joint model is used for representing the generated energy relation of the wind motors and comprises the real-time generated energy relation of the wind motors; predicting the real-time power generation amounts of a plurality of wind power motors one by one based on a power generation amount prediction model to obtain predicted power generation amounts; predicting the wind speed under the same time based on a wind speed prediction model to obtain a predicted wind speed under a prediction condition, and obtaining a plurality of target predicted wind speeds corresponding to the wind motors based on the predicted wind speed and a wind speed relation model; and obtaining the predicted power generation amount of the wind power generation field based on the target predicted wind speed and the predicted power generation amount combined with a target motor combined model.
According to the first implementation manner, the power generation amount prediction model comprises an input layer, an implicit layer and an output layer, the number of the neuron nodes of the input layer is 23, the number of the neuron nodes of the output layer is 1, the number of the neuron nodes of the implicit layer is 10, and the activation functions of the implicit layer and the output layer are respectively a tan sig function and a purelin function.
With reference to the first possible implementation manner of the first aspect, in a second possible implementation manner, the method for constructing the power generation amount prediction model includes: acquiring historical actual data and weather forecast data of a wind power plant; the historical actual data comprises actual operation data of the full-field fan; the weather forecast data comprise wind speed, temperature, humidity, wind direction cosine value and air pressure data; and training the weather forecast data as the input of the power generation amount prediction model, and completing training convergence when the training result meets the preset learning rate and the preset error to obtain the power generation amount prediction model.
With reference to the second possible implementation manner of the first aspect, in a third possible implementation manner, the learning rate is 0.05, and the preset error is 0.001.
According to a fourth implementation manner, the wind speed prediction model is formed based on training, and the training method comprises: acquiring a target measured sample wind speed of a target electric field and sample wind speed data of an upstream electric field in an upstream area corresponding to the target electric field; determining a sample wind speed group comprising a plurality of upstream sample wind speed data according to a wind path time interval between the target electric field and an upstream electric field in the upstream region; according to the target actually measured sample wind speed and the sample wind speed group, training is carried out by carrying out parameter adjustment on an initial wind speed prediction model, and when a preset training condition is reached, the training is ended, so that a wind speed prediction model is obtained.
With reference to the fourth possible implementation manner of the first aspect, in a fifth possible implementation manner, the upstream electric field and the wind path time interval are determined by a method including the following steps: acquiring a first measured wind speed of a target electric field in a first period; acquiring second measured wind speeds of all electric fields except the target electric field at preset time intervals in each wind speed acquisition period respectively; calculating a correlation value of the first measured wind speed and each second measured wind speed according to a preset association relation; if the correlation value is greater than a preset correlation threshold, determining that the electric field except the target electric field corresponding to the correlation value is an upstream electric field and the wind path time interval corresponding to the upstream electric field.
With reference to the fifth possible implementation manner of the first aspect, in a sixth possible implementation manner, the upstream area is determined by a method including the following steps: determining all upstream electric fields of the target electric field; clustering all upstream electric fields of the target electric field into a plurality of upstream areas according to a preset clustering method; the upstream electric field in each upstream area is within a preset geographical position range; an upstream region is defined among the plurality of upstream regions.
With reference to the fourth possible implementation manner of the first aspect, in a seventh possible implementation manner, the determining, according to a wind path time interval between the target electric field and an upstream electric field in the upstream area, a sample wind speed group including a number of sample wind speed data includes: acquiring a minimum wind path time interval and a maximum wind path time interval corresponding to an upstream electric field in an upstream region; and determining the upstream sample wind speed data one by one between the minimum wind path time interval and the maximum wind path time interval according to a preset time step.
With reference to the fourth possible implementation manner of the first aspect, in an eighth possible implementation manner, the step of obtaining a target measured sample wind speed of the target electric field includes: taking the numerical forecast wind speed obtained by numerical forecast prediction as a target actual measurement sample wind speed.
In a second aspect, a wind farm power generation amount prediction system is applied to a wind farm, and the wind farm comprises a plurality of wind power generation motors; the system comprises: the real-time data acquisition device comprises an environment data module arranged at the sides of a plurality of wind power generation motors and is used for acquiring real-time environment data of the wind power generation motors, wherein the real-time environment data comprises wind speed data, temperature data, humidity data, wind direction cosine value data and air pressure data; and the prediction device is configured with a wind speed prediction model for predicting the wind speed of the power generation field, a power generation amount prediction model for predicting the power generation amounts of the power generation motors, and a motor combination model for acquiring the predicted power generation amount of the power generation field based on the predicted wind speed of the power generation field and the power generation amounts of the power generation motors.
In a third aspect, there is provided a terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, the processor implementing the method of any one of the preceding claims when executing the computer program.
In a fourth aspect, a computer-readable storage medium is provided, the computer-readable storage medium storing a computer program which, when executed by a processor, implements a method as claimed in any one of the preceding claims.
In the technical scheme provided by the embodiment of the application, the prediction of the power generation amount of the single wind power motor is realized by configuring the prediction model related to each wind power motor, and the prediction result of the overall power generation amount of the power generation field is obtained by configuring the overall wind speed model and the motor combined model, so that the prediction accuracy of the overall power generation amount is improved.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings that are needed 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 application, and that other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.
The methods, systems, and/or programs in the accompanying drawings will be described further in terms of exemplary embodiments. These exemplary embodiments will be described in detail with reference to the drawings. These exemplary embodiments are non-limiting exemplary embodiments, wherein the exemplary numbers represent like mechanisms throughout the various views of the drawings.
Fig. 1 is a schematic structural diagram of a system provided in an embodiment of the present application.
FIG. 2 is a flow chart of a wind farm power generation prediction method, as shown in some embodiments of the present application.
Fig. 3 is a block schematic diagram of an apparatus provided according to an embodiment of the present application.
Detailed Description
In order to better understand the technical solutions described above, the following detailed description of the technical solutions of the present application is provided through the accompanying drawings and specific embodiments, and it should be understood that the specific features of the embodiments and embodiments of the present application are detailed descriptions of the technical solutions of the present application, and not limit the technical solutions of the present application, and the technical features of the embodiments and embodiments of the present application may be combined with each other without conflict.
In the following detailed description, numerous specific details are set forth by way of examples in order to provide a thorough understanding of the relevant teachings. However, it will be apparent to one skilled in the art that the present application may be practiced without these details. In other instances, well-known methods, procedures, systems, components, and/or circuits have been described at a relatively high-level, without detail, in order to avoid unnecessarily obscuring aspects of the present application.
The flowcharts are used in this application to describe implementations performed by systems according to embodiments of the present application. It should be clearly understood that the execution of the flowcharts may be performed out of order. Rather, these implementations may be performed in reverse order or concurrently. Additionally, at least one other execution may be added to the flowchart. One or more of the executions may be deleted from the flowchart.
Before describing embodiments of the present invention in further detail, the terms and terminology involved in the embodiments of the present invention will be described, and the terms and terminology involved in the embodiments of the present invention will be used in the following explanation.
(1) In response to a condition or state that is used to represent the condition or state upon which the performed operation depends, the performed operation or operations may be in real-time or with a set delay when the condition or state upon which it depends is satisfied; without being specifically described, there is no limitation in the execution sequence of the plurality of operations performed.
(2) Based on the conditions or states that are used to represent the operations that are being performed, one or more of the operations that are being performed may be in real-time or with a set delay when the conditions or states that are being relied upon are satisfied; without being specifically described, there is no limitation in the execution sequence of the plurality of operations performed.
(3) Convolutional neural networks are a class of feedforward neural networks that involve convolutional computations and have a deep structure. Convolutional neural networks are proposed by biological Receptive Field (fielded) mechanisms. Convolutional neural networks are dedicated to neural networks that process data having a grid-like structure. For example, time-series data (which may be regarded as a one-dimensional grid formed by regularly sampling on a time axis) and image data (which may be regarded as a two-dimensional grid of pixels), the convolutional neural network employed in the present embodiment processes the image data.
According to the technical scheme provided by the embodiment of the application, the main application scene is the obtaining of the whole power generation quantity prediction result of the wind power generation field. In order to develop and utilize wind energy in a large scale, the wind power must be accurately predicted. The wind power prediction can enable wind power enterprises and power dispatching departments to jointly dispatch, so that more wind power can be used for surfing the Internet and safe operation of a power grid is ensured. Today, wind power prediction technology is one of the key technologies for wind power industry development. Since 2000, the wind power industry in China is vigorously developed, the wind power internet surfing scale is continuously enlarged, and the influence of the fluctuation, the randomness and the intermittence of the wind power internet surfing scale is larger and larger.
In the prior art, the early development of wind power prediction technology is referred to by the load prediction technology, which is a mature prediction technology at the time. Wind power prediction technology in this period is rapidly developed, but the prediction technology in this period is based on a single model. Wind power prediction is generally performed by only one prediction model, and the prediction results of multiple models are not combined. The prediction method comprises an autoregressive method, a linear extrapolation method, a Kalman filtering method and other different models. The models can predict wind power to a certain extent, but the prediction accuracy is poor, the prediction duration is short, and the prediction value is low.
The wind speed can be predicted by a numerical weather method, weather information such as wind speed, wind direction and the like is predicted by a Landberg reasoning method in the 90 th year of the 20 th century, then the wind speed result is corrected by some algorithms, and finally the output power is obtained according to a wind speed-power curve. Since the 20 th century, with the widespread popularity of computer technology and the continuous development of artificial intelligence theory, wind power prediction has been slowly performed by means of intelligent computation. Such as a time series method, a neural network prediction method, a wavelet analysis prediction method, a genetic algorithm prediction and other prediction algorithm models. In the prior art, a time sequence method can be utilized to predict wind speed data, and the obtained result wind speed is used as an input variable of a neural network, so that the prediction precision is finally improved. By establishing an error and prediction model based on a neural network, the simultaneous prediction processing of the error and the wind power is realized. Based on the quantile regression analysis theory, the wind power fluctuation interval is analyzed, a quantile regression prediction model is established, and the prediction of the wind power fluctuation interval is realized. The non-parameter confidence interval estimation method based on the statistical analysis of the prediction error distribution characteristics improves the prediction accuracy. The method combining wavelet transformation and artificial neural network can be used for predicting the generating capacity of the fan, and the time delay problem in wind power prediction is solved. But the prediction accuracy is not sufficient. In other prior art, the best prediction effect is obtained by comparing the prediction performances of a Long Short-Term Memory (LSTM) model, an artificial neural network (Artificial Neural Network, ANN) model and a support vector machine (SupportVector Machine, SVM) model. The difference of wind power change rules of different wind power plants is not considered. The algorithm utilizes different structural designs to extract different characteristics of the data, and the principle of the algorithm is quite different, but the prediction effect still can not fully meet the actual requirements of wind power enterprises. In recent years, more researchers have combined two or more prediction methods, and these prediction methods are called a combined prediction method. The combined prediction further improves the wind power prediction quality. It is also possible to combine a prediction method based on statistical prediction with a prediction method based on physical methods. The representative method of wind power prediction based on a physical method is a prediction method based on numerical weather, the basic idea is to directly model by utilizing local topography and landform, solve a high-dimensional equation set by utilizing fluid mechanics by means of weather prediction information, and directly obtain wind speed prediction. And finally, obtaining power prediction data by utilizing a wind speed-power curve. The prediction quality of the model is closely related to the weather parameter prediction, and the more accurate weather prediction information is difficult to obtain, so that the method is suitable for a large-scale wind power base, and the input research and development cost is relatively high; the prediction quality is generally better than that based on statistical methods, especially for long-term wind power. The prediction method based on statistical learning generally has a rapid decrease in the prediction effect when predicting wind power for a long time. This is mainly due to the insufficient extraction of data features by the model.
Therefore, based on the above technical background, the present embodiment adopts a combined prediction model and a model in which related factors affect each other to obtain a prediction result of the power generation amount of the power generation field.
In this embodiment, the present embodiment provides a terminal device 100, which includes a memory 110, a processor 120, and a computer program stored in the memory and executable on the processor, wherein the processor executes a prediction result that obtains a final power generation amount based on a plurality of acquired real-time data. In this embodiment, the terminal device communicates with the user terminal, and transmits the acquired detection information to the corresponding user terminal, so as to implement transmission of the detection information on hardware. The method is based on network implementation aiming at the information sending mode, and an association relation between the user terminal and the terminal equipment is required to be established before the terminal equipment is applied, and the association between the terminal equipment and the user terminal can be realized through a registration mode. The terminal device can be aimed at a plurality of user terminals or one user terminal, and the user terminal communicates with the terminal device through passwords and other encryption modes.
In this embodiment, the terminal may be a server, and includes a memory, a processor, and a communication unit for the physical structure of the server. The memory, the processor and the communication unit are electrically connected with each other directly or indirectly to realize data transmission or interaction. For example, the components may be electrically connected to each other via one or more communication buses or signal lines. The memory is used for storing specific information and programs, and the communication unit is used for sending the processed information to the corresponding user side.
In this embodiment, the storage module is divided into two storage areas, where one storage area is a program storage unit and the other storage area is a data storage unit. The program storage unit is equivalent to a firmware area, the read-write authority of the area is set to be in a read-only mode, and the data stored in the area can not be erased and changed. And the data in the data storage unit can be erased or read and written, and when the capacity of the data storage area is full, the newly written data can cover the earliest historical data.
The Memory may be, but is not limited to, random access Memory (Random Access Memory, RAM), read Only Memory (ROM), programmable Read Only Memory (Programmable Read-Only Memory, PROM), erasable Read Only Memory (Erasable Programmable Read-OnlyMemory, EPROM), electrically erasable Read Only Memory (Ele ultrasound ric Erasable Programmable Read-Only Memory, EEPROM), etc.
The processor may be an integrated circuit chip having signal processing capabilities. The processor may be a general-purpose processor, including a central processing unit (Central Processing Unit, CPU), a network processor (Network Processor, NP), etc.; but also Digital Signal Processors (DSPs)), application Specific Integrated Circuits (ASICs), field Programmable Gate Arrays (FPGAs) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components. The disclosed methods, steps, and logic blocks in the embodiments of the present invention may be implemented or performed. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
Referring to fig. 2, in this embodiment, for a method for predicting the power generation amount of a wind farm based on machine learning, the working logic is to obtain the predicted power generation amounts of a plurality of power generation motors in the wind farm and the predicted wind speeds in the wind farm, obtain the independent predicted wind speeds of the corresponding power generation motors based on the joint model of the plurality of power generation motors, and obtain the overall predicted power generation amount of the final wind farm based on the above data. The method specifically comprises the following steps:
and S210, predicting the real-time power generation amounts of the wind power motors one by one based on the power generation amount prediction model to obtain predicted power generation amounts.
In this embodiment, the power generation amount prediction model includes an input layer, an implicit layer and an output layer, the number of neuronal nodes of the input layer is 23, the number of neuronal nodes of the output layer is 1, the number of neuronal nodes of the implicit layer is 10, and activation functions of the implicit layer and the output layer are respectively a tansig function and a purelin function.
In the embodiment, the basic structure of the power generation amount prediction model is a BP neural network, and the BP neural network is optimized based on a genetic algorithm, so that training of the BP neural network is realized through genetic algorithm optimization.
The workflow for the genetic algorithm specifically comprises the following parts:
(1) The weight, the threshold, the encoding length of the chromosome and the number of neurons of the hidden layer, the number of layers and the number of neurons of each layer of the BP neural network are required to be set according to the type and the number of input data, and in the embodiment, the number of neurons of the input layer is set to be equal to the type number of the input data, and the number of neurons of the output layer is set to be equal to the type number of the output data. In this embodiment, the input data types include wind speed, temperature, humidity, wind direction cosine value, air pressure data, and the number of weights and thresholds and the encoding length of the chromosome are calculated by the following formula:
N w ＝n input ·n hide +n hide ·n output ；
N b ＝n hide +n output ；
l＝N w +N b 。
wherein N is w N is the number of weight values b N is the number of threshold values input N is the number of neurons of the input layer hide N is the number of hidden layer neurons output For the number of output layer neurons, l is the coding length of the chromosome of the genetic algorithm.
In this embodiment, the power generation amount prediction model includes an input layer, an implicit layer, and an output layer, where the number of neuronal nodes of the input layer is 23, the number of neuronal nodes of the output layer is 1, the number of neuronal nodes of the implicit layer is 10, and activation functions of the implicit layer and the output layer are respectively a tansig function and a purelin function.
Also, the construction method provided in the present embodiment regarding the power generation amount prediction model includes:
acquiring historical actual data and weather forecast data of a wind power plant; the historical actual data comprises actual operation data of the full-field fan; the weather forecast data comprise wind speed, temperature, humidity, wind direction cosine value and air pressure data;
and training the weather forecast data as the input of the power generation amount prediction model, and completing training convergence when the training result meets the preset learning rate and the preset error to obtain the power generation amount prediction model. The number of weights of the neural network is 23×10+10×1=240, the number of thresholds is 10+1=11, the individual coding length of the genetic algorithm is 240+11=251, the initial population size is 50, the arithmetic crossover probability is 0.6, the non-uniform mutation probability is 0.1, and the maximum evolution algebra is 50 generations.
S220, predicting the wind speed under the same time based on a wind speed prediction model to obtain a predicted wind speed under a prediction condition, and obtaining a plurality of target predicted wind speeds corresponding to the wind motors based on the predicted wind speed and a wind speed relation model.
In this embodiment, the wind speed prediction model is formed based on training, and the training method includes: acquiring a target measured sample wind speed of a target electric field and sample wind speed data of an upstream electric field in an upstream area corresponding to the target electric field; determining a sample wind speed group comprising a plurality of upstream sample wind speed data according to a wind path time interval between the target electric field and an upstream electric field in the upstream region; and training the target actually measured sample wind speed and the sample wind speed group by carrying out parameter adjustment on an initial wind speed prediction model, and ending the training when a preset training condition is reached to obtain a wind speed prediction model.
In this embodiment, the upstream electric field and the wind path time interval are determined by a method comprising the steps of: acquiring a first measured wind speed of a target electric field in a first period; acquiring second measured wind speeds of all electric fields except the target electric field at preset time intervals in each wind speed acquisition period respectively; calculating a correlation value of the first measured wind speed and each second measured wind speed according to a preset association relation; if the correlation value is greater than a preset correlation threshold, determining that the electric field except the target electric field corresponding to the correlation value is an upstream electric field and the wind path time interval corresponding to the upstream electric field.
In this embodiment, the upstream region is determined by a method comprising the steps of: determining all upstream electric fields of the target electric field; clustering all upstream electric fields of the target electric field into a plurality of upstream areas according to a preset clustering method; the upstream electric field in each upstream area is within a preset geographical position range; an upstream region is defined among the plurality of upstream regions.
In this embodiment, the determining a sample wind speed group including a number of sample wind speed data according to a wind path time interval between the target electric field and an upstream electric field in the upstream region includes: acquiring a minimum wind path time interval and a maximum wind path time interval corresponding to an upstream electric field in an upstream region; and determining the upstream sample wind speed data one by one between the minimum wind path time interval and the maximum wind path time interval according to a preset time step.
In this embodiment, the specific step of acquiring the target measured sample wind speed of the target electric field includes: taking the numerical forecast wind speed obtained by numerical forecast prediction as a target actual measurement sample wind speed.
S230, acquiring real-time power generation amounts of a plurality of wind motors and a plurality of real-time wind speed information corresponding to the wind motors in a wind power plant under the same time, constructing a wind speed relation model corresponding to the wind motors based on the plurality of real-time wind speed information and standard real-time wind speed information, and correcting a motor joint model based on the real-time wind speed information and the wind speed relation model to obtain a target motor joint model, wherein the motor joint model is used for representing the power generation amount relation of the wind motors, and comprises the relation of the real-time power generation amounts of the wind motors;
s240, obtaining the predicted power generation amount of the wind power generation field based on the target predicted wind speed and the predicted power generation amount combined with a target motor combined model.
Referring to fig. 3, the present embodiment further provides a wind farm power generation amount prediction system 300, which is applied to a wind farm, where the wind farm includes a plurality of wind power generation motors.
In this embodiment, the system includes a real-time data acquisition device 310 and a prediction device 320. Wherein the real-time data acquisition device 310 comprises an environment data module arranged at the side of the plurality of wind power generation motors for acquiring real-time environment data of the plurality of wind power generation motors, wherein the real-time environment data comprises wind speed data, temperature data, humidity data, wind direction cosine value data and air pressure data. In the present embodiment, the prediction device 320 is configured with a wind speed prediction model 321 for predicting a wind speed of a power plant, a power generation amount prediction model 322 for predicting a power generation amount of a power generation motor, and a motor combination model 323 for obtaining predicted power generation amounts of a power generation field based on the wind speed of the predicted power generation field and the power generation amounts of a plurality of power generation motors.
In the technical scheme provided by the embodiment of the application, the prediction of the power generation amount of the single wind power motor is realized by configuring the prediction model related to each wind power motor, and the prediction result of the overall power generation amount of the power generation field is obtained by configuring the overall wind speed model and the motor combined model, so that the prediction accuracy of the overall power generation amount is improved.
It is to be understood that the terminology which is not explained by terms of nouns in the foregoing description is not intended to be limiting, as those skilled in the art can make any arbitrary deduction from the foregoing disclosure.
The person skilled in the art can undoubtedly determine technical features/terms of some preset, reference, predetermined, set and preference labels, such as threshold values, threshold value intervals, threshold value ranges, etc., from the above disclosure. For some technical feature terms which are not explained, a person skilled in the art can reasonably and unambiguously derive based on the logical relation of the context, so that the technical scheme can be clearly and completely implemented. The prefixes of technical feature terms, such as "first", "second", "example", "target", etc., which are not explained, can be unambiguously deduced and determined from the context. Suffixes of technical feature terms, such as "set", "list", etc., which are not explained, can also be deduced and determined unambiguously from the context.
The foregoing of the disclosure of the embodiments of the present application will be apparent to and complete with respect to those skilled in the art. It should be appreciated that the process of deriving and analyzing technical terms not explained based on the above disclosure by those skilled in the art is based on what is described in the present application, and thus the above is not an inventive judgment of the overall scheme.
While the basic concepts have been described above, it will be apparent to those skilled in the art that the foregoing detailed disclosure is by way of example only and is not intended to be limiting. Although not explicitly described herein, various modifications, improvements, and adaptations may occur to one skilled in the art. Such modifications, improvements, and modifications are intended to be suggested within this application, and are therefore within the spirit and scope of the exemplary embodiments of this application.
Meanwhile, the present application uses specific terminology to describe embodiments of the present application. Reference to "one embodiment," "an embodiment," and/or "some embodiments" means that a particular feature, structure, or characteristic is associated with at least one embodiment of the present application. Thus, it should be emphasized and should be appreciated that two or more references to "an embodiment" or "one embodiment" or "an alternative embodiment" in various portions of this specification are not necessarily all referring to the same embodiment. Furthermore, certain features, structures, or characteristics of at least one embodiment of the present application may be combined as suitable.
In addition, those of ordinary skill in the art will understand that the various aspects of the present application may be illustrated and described in terms of several patentable categories or cases, including any novel and useful processes, machines, products, or combinations of materials, or any novel and useful improvements thereto. Accordingly, aspects of the present application may be performed entirely by hardware, entirely by software (including firmware, resident software, micro-code, etc.) or by a combination of hardware and software. The above hardware or software may be referred to as a "unit," component, "or" system. Furthermore, aspects of the present application may be embodied as a computer product in at least one computer-readable medium, the product comprising computer-readable program code.
The computer readable signal medium may comprise a propagated data signal with computer program code embodied therein, for example, on a baseband or as part of a carrier wave. The propagated signal may take on a variety of forms, including electro-magnetic, optical, etc., or any suitable combination thereof. A computer readable signal medium may be any computer readable medium that is not a computer readable storage medium and that can communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device. Program code located on a computer readable signal medium may be propagated through any suitable medium including radio, electrical, fiber optic, RF, or the like, or any combination of the foregoing.
Computer program code required for execution of aspects of the present application may be written in any combination of one or more programming languages, including an object oriented programming such as Java, scala, smalltalk, eiffel, JADE, emerald, C ++, c#, vb net, python, etc., or similar conventional programming languages such as the "C" programming language, visual Basic, fortran 2003,Perl,COBOL 2002,PHP,ABAP, dynamic programming languages such as Python, ruby and Groovy or other programming languages. The programming code may execute entirely on the user's computer, or as a stand-alone software package, or partly on the user's computer and partly on a remote computer or entirely on the remote computer or server. In the latter scenario, the remote computer may be connected to the user's computer through any form of network, such as a Local Area Network (LAN) or a Wide Area Network (WAN), or the connection may be made to an external computer (for example, through the Internet), or in a cloud computing environment, or as a service, such as software as a service (SaaS).
Furthermore, the order in which the processing elements and sequences are described, the use of numerical letters, or other designations are used is not intended to limit the order in which the processes and methods of the present application are performed, unless specifically indicated in the claims. While in the foregoing disclosure there has been discussed, by way of various examples, some embodiments of the invention which are presently considered to be useful, it is to be understood that this detail is solely for that purpose and that the appended claims are not limited to the disclosed embodiments, but, on the contrary, are intended to cover all modifications and equivalent arrangements that are within the spirit and scope of the embodiments of this application. For example, while the system components described above may be implemented by hardware devices, they may also be implemented solely by software solutions, such as installing the described system on an existing server or mobile device.
It should also be appreciated that in the foregoing description of the embodiments of the present application, various features are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of at least one of the embodiments of the invention. This method of disclosure, however, is not intended to imply that more features than are presented in the claims are required for the subject application. Indeed, less than all of the features of a single embodiment disclosed above.
Claims (6)
1. A machine learning-based wind farm power generation amount prediction method, comprising:
acquiring real-time power generation amounts of a plurality of wind motors and a plurality of real-time wind speed information corresponding to the wind motors in a wind power plant under the same time, constructing a wind speed relation model corresponding to the wind motors based on the plurality of real-time wind speed information and standard real-time wind speed information, and correcting a motor joint model based on the real-time wind speed information and the wind speed relation model to obtain a target motor joint model, wherein the motor joint model is used for representing the power generation amount relation of the wind motors and comprises the real-time power generation amount relation of the wind motors;
predicting the real-time power generation amounts of a plurality of wind power motors one by one based on a power generation amount prediction model to obtain predicted power generation amounts;
predicting the wind speed under the same time based on a wind speed prediction model to obtain a predicted wind speed under a prediction condition, and obtaining a plurality of target predicted wind speeds corresponding to the wind motors based on the predicted wind speed and a wind speed relation model;
obtaining the predicted power generation amount of the wind power generation field based on the target predicted wind speed and the predicted power generation amount combined with a target motor combined model;
the generating capacity prediction model comprises an input layer, an implicit layer and an output layer, wherein the number of the neuron nodes of the input layer is 23, the number of the neuron nodes of the output layer is 1, the number of the neuron nodes of the implicit layer is 10, and the activation functions of the implicit layer and the output layer are respectively a tan sig function and a purelin function;
the method for constructing the power generation amount prediction model comprises the following steps:
acquiring historical actual data and weather forecast data of a wind power plant; the historical actual data comprises actual operation data of the full-field fan; the weather forecast data comprise wind speed, temperature, humidity, wind direction cosine value and air pressure data;
training the weather forecast data as the input of the generating capacity prediction model, and completing training convergence when a training result meets a preset learning rate and a preset error to obtain the generating capacity prediction model;
the learning rate is 0.05, and the preset error is 0.001.
2. The machine learning based wind farm power generation prediction method of claim 1, wherein the wind speed prediction model is based on a training composition, the training method comprising:
acquiring a target measured sample wind speed of a target electric field and sample wind speed data of an upstream electric field in an upstream area corresponding to the target electric field;
determining a sample wind speed group comprising a plurality of upstream sample wind speed data according to a wind path time interval between the target electric field and an upstream electric field in the upstream region;
according to the target actually measured sample wind speed and the sample wind speed group, training is carried out by carrying out parameter adjustment on an initial wind speed prediction model, and when a preset training condition is reached, the training is ended, so that a wind speed prediction model is obtained.
3. The machine learning based wind farm power generation prediction method of claim 2, wherein the upstream farm and the wind path time interval are determined by a method comprising:
acquiring a first measured wind speed of a target electric field in a first period;
acquiring second measured wind speeds of all electric fields except the target electric field at preset time intervals in each wind speed acquisition period respectively;
calculating a correlation value of the first measured wind speed and each second measured wind speed according to a preset association relation;
if the correlation value is greater than a preset correlation threshold, determining that the electric field except the target electric field corresponding to the correlation value is an upstream electric field and the wind path time interval corresponding to the upstream electric field.
4. A machine learning based wind farm power generation prediction method according to claim 3, wherein the upstream region is determined by a method comprising the steps of:
determining all upstream electric fields of the target electric field;
clustering all upstream electric fields of the target electric field into a plurality of upstream areas according to a preset clustering method; the upstream electric field in each upstream area is within a preset geographical position range;
an upstream region is defined among the plurality of upstream regions.
5. The machine learning based wind farm power generation prediction method of claim 4, wherein the determining a sample wind speed set comprising a number of sample wind speed data based on a wind path time interval between the target farm and an upstream farm in the upstream area comprises:
acquiring a minimum wind path time interval and a maximum wind path time interval corresponding to an upstream electric field in an upstream region;
and determining the upstream sample wind speed data one by one between the minimum wind path time interval and the maximum wind path time interval according to a preset time step.
6. The machine learning based wind farm power generation prediction method of claim 5, wherein the step of obtaining a target measured sample wind speed for a target farm comprises: taking the numerical forecast wind speed obtained by numerical forecast prediction as a target actual measurement sample wind speed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211607591.XA CN115829140B (en) | 2022-12-14 | 2022-12-14 | Wind power generation plant power generation amount prediction method and system based on machine learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211607591.XA CN115829140B (en) | 2022-12-14 | 2022-12-14 | Wind power generation plant power generation amount prediction method and system based on machine learning |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115829140A CN115829140A (en) | 2023-03-21 |
| CN115829140B true CN115829140B (en) | 2023-07-25 |
Family
ID=85547312
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211607591.XA Active CN115829140B (en) | 2022-12-14 | 2022-12-14 | Wind power generation plant power generation amount prediction method and system based on machine learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115829140B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103268366A (en) * | 2013-03-06 | 2013-08-28 | 辽宁省电力有限公司电力科学研究院 | Combined wind power prediction method suitable for distributed wind power plant |
| CN103683274A (en) * | 2013-07-16 | 2014-03-26 | 国家电网公司 | Regional long-term wind power generation capacity probability prediction method |
| JPWO2016121202A1 (en) * | 2015-01-30 | 2017-11-09 | 日本電気株式会社 | Prediction device, prediction method, and program |
| CN109087215A (en) * | 2018-08-09 | 2018-12-25 | 国网山东省电力公司经济技术研究院 | More Power Output for Wind Power Field joint probability density prediction techniques |
| CN109726802A (en) * | 2018-12-29 | 2019-05-07 | 中南大学 | A kind of railway and wind power plant environment wind speed machine learning prediction technique |
| CN112434848A (en) * | 2020-11-19 | 2021-03-02 | 西安理工大学 | Nonlinear weighted combination wind power prediction method based on deep belief network |
| CN112580900A (en) * | 2021-02-23 | 2021-03-30 | 国能日新科技股份有限公司 | Short-term power prediction method and system based on single fan modeling |
| CN113379142A (en) * | 2021-06-23 | 2021-09-10 | 西安理工大学 | Short-term wind power prediction method based on wind speed correction and fusion model |
| JP2021182319A (en) * | 2020-05-20 | 2021-11-25 | 株式会社日立製作所 | Prediction apparatus and prediction method |
| CN115271253A (en) * | 2022-09-05 | 2022-11-01 | 中国长江三峡集团有限公司 | Water-wind power generation power prediction model construction method and device and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10598157B2 (en) * | 2017-02-07 | 2020-03-24 | International Business Machines Corporation | Reducing curtailment of wind power generation |
-
2022
- 2022-12-14 CN CN202211607591.XA patent/CN115829140B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103268366A (en) * | 2013-03-06 | 2013-08-28 | 辽宁省电力有限公司电力科学研究院 | Combined wind power prediction method suitable for distributed wind power plant |
| CN103683274A (en) * | 2013-07-16 | 2014-03-26 | 国家电网公司 | Regional long-term wind power generation capacity probability prediction method |
| JPWO2016121202A1 (en) * | 2015-01-30 | 2017-11-09 | 日本電気株式会社 | Prediction device, prediction method, and program |
| CN109087215A (en) * | 2018-08-09 | 2018-12-25 | 国网山东省电力公司经济技术研究院 | More Power Output for Wind Power Field joint probability density prediction techniques |
| CN109726802A (en) * | 2018-12-29 | 2019-05-07 | 中南大学 | A kind of railway and wind power plant environment wind speed machine learning prediction technique |
| JP2021182319A (en) * | 2020-05-20 | 2021-11-25 | 株式会社日立製作所 | Prediction apparatus and prediction method |
| CN112434848A (en) * | 2020-11-19 | 2021-03-02 | 西安理工大学 | Nonlinear weighted combination wind power prediction method based on deep belief network |
| CN112580900A (en) * | 2021-02-23 | 2021-03-30 | 国能日新科技股份有限公司 | Short-term power prediction method and system based on single fan modeling |
| CN113379142A (en) * | 2021-06-23 | 2021-09-10 | 西安理工大学 | Short-term wind power prediction method based on wind speed correction and fusion model |
| CN115271253A (en) * | 2022-09-05 | 2022-11-01 | 中国长江三峡集团有限公司 | Water-wind power generation power prediction model construction method and device and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115829140A (en) | 2023-03-21 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Liu et al. | Ensemble forecasting system for short-term wind speed forecasting based on optimal sub-model selection and multi-objective version of mayfly optimization algorithm | |
| Zhang et al. | Short-term wind speed interval prediction based on artificial intelligence methods and error probability distribution | |
| Jung et al. | Prediction of building energy consumption using an improved real coded genetic algorithm based least squares support vector machine approach | |
| Zhang et al. | A comprehensive wind speed prediction system based on Monte Carlo and artificial intelligence algorithms | |
| Devi et al. | Hourly day-ahead wind power forecasting with the EEMD-CSO-LSTM-EFG deep learning technique | |
| Tian et al. | A combination forecasting model of wind speed based on decomposition | |
| CN102663513B (en) | Utilize the wind power combined prediction modeling method of grey relational grade analysis | |
| Yin et al. | Deep forest regression for short-term load forecasting of power systems | |
| US20230037193A1 (en) | Wind power output interval prediction method | |
| CN106875033A (en) | A kind of wind-powered electricity generation cluster power forecasting method based on dynamic self-adapting | |
| CN112100911B (en) | Solar radiation prediction method based on depth BILSTM | |
| CN108428017A (en) | Wind power interval prediction method based on core extreme learning machine quantile estimate | |
| Yuan et al. | Conditional style-based generative adversarial networks for renewable scenario generation | |
| Sengar et al. | Ensemble approach for short term load forecasting in wind energy system using hybrid algorithm | |
| CN104463356A (en) | Photovoltaic power generation power prediction method based on multi-dimension information artificial neural network algorithm | |
| CN110705771A (en) | Method and device for predicting and optimizing power generation power of new energy of regional power grid | |
| CN114676941B (en) | Electric-thermal load combined self-adaptive prediction method and device for park comprehensive energy system | |
| El Bourakadi et al. | Improved extreme learning machine with AutoEncoder and particle swarm optimization for short-term wind power prediction | |
| Teferra et al. | Fuzzy-based prediction of solar PV and wind power generation for microgrid modeling using particle swarm optimization | |
| Zhang et al. | Interval prediction of ultra-short-term photovoltaic power based on a hybrid model | |
| CN116014722A (en) | Sub-solar photovoltaic power generation prediction method and system based on seasonal decomposition and convolution network | |
| Wu et al. | Deterministic and probabilistic wind power forecasts by considering various atmospheric models and feature engineering approaches | |
| Peng et al. | A short‐term wind power prediction method based on deep learning and multistage ensemble algorithm | |
| Alharbi et al. | Short-term wind speed and temperature forecasting model based on gated recurrent unit neural networks | |
| Bi et al. | Accurate water quality prediction with attention-based bidirectional LSTM and encoder–decoder |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |