CN115936924A - Wind power plant wind energy prediction method and system - Google Patents
Wind power plant wind energy prediction method and system Download PDFInfo
- Publication number
- CN115936924A CN115936924A CN202211607577.XA CN202211607577A CN115936924A CN 115936924 A CN115936924 A CN 115936924A CN 202211607577 A CN202211607577 A CN 202211607577A CN 115936924 A CN115936924 A CN 115936924A
- Authority
- CN
- China
- Prior art keywords
- wind energy
- wind
- equipment
- power plant
- electric
- 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.)
- Granted
Links
Images
Landscapes
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The invention provides a wind power prediction method and a wind power prediction system for a wind power plant, and relates to the technical field of wind power generation. The method comprises the following steps: the method comprises the steps of firstly, obtaining historical capacity data of fan equipment and estimated weather data of a next period of an area where a wind power plant is located, constructing a first input characteristic according to the historical capacity data of the fan equipment and the estimated weather data of the next period of the area where the wind power plant is located, then obtaining a synchronous stable value of a current period of the power equipment, constructing a second input characteristic according to the synchronous stable value of the current period of the power equipment, and finally inputting the first input characteristic and the second input characteristic into a wind energy data prediction model obtained through pre-training and outputting actual output wind energy prediction data of the next period of the wind power plant. In the invention, the influence of the power equipment on the actual output electric energy of the wind power plant in the operation process is also used as a reference condition for predicting the actual output wind energy data of the wind power plant, so that the prediction result is more accurate.
Description
Technical Field
The invention relates to the technical field of wind power generation, in particular to a wind power prediction method and a wind power prediction system for a wind power plant.
Background
In modern life, with the continuous tension of energy situation, new energy has been paid unprecedented attention. The new energy becomes the industry which is highly regarded by China and even the countries with deficient global resources, and the wind power generation is rapidly developed due to a plurality of advantages of the soil, and the wind power cost is expected to be further reduced along with the localization and scale of the wind power installation in China. Wind power will therefore become the backbone industry for future power.
In the related art, when wind energy prediction is carried out on a wind power plant, only the actual power generation amount of a wind turbine generator is predicted, and the influence of various electric equipment in the wind power plant on the actual output electric energy of the wind power plant in the operation process is avoided.
Disclosure of Invention
The embodiment of the invention provides a wind power plant wind energy prediction method and system, and aims to solve or partially solve the problems in the background technology.
In order to solve the technical problem, the invention is realized as follows:
in a first aspect, an embodiment of the present invention provides a method for predicting wind energy of a wind farm, where the method includes:
obtaining historical productivity data of fan equipment and estimated weather data of the next period of an area where a wind power plant is located;
constructing a first input characteristic according to historical capacity data of the fan equipment and estimated weather data of the next period of an area where the wind farm is located;
acquiring a synchronous stable value of the current period of the power equipment, and constructing a second input characteristic according to the synchronous stable value of the current period of the power equipment, wherein the synchronous stable value is used for representing a connection stable state of the power equipment and a wind power plant;
and inputting the first input characteristic and the second input characteristic into a wind energy data prediction model obtained by pre-training, and outputting actual output wind energy prediction data of the next period of the wind power plant.
Optionally, the step of obtaining a synchronous steady value of the current cycle of the power equipment comprises:
calculating an impedance voltage drop parameter of the electric equipment in the current period according to the electric operation parameter of the electric equipment in the current period;
calculating reactive compensation characteristic parameters of the current period of the electric equipment according to the influence capacity of the electric equipment on the fan equipment when the electric equipment executes reactive compensation;
and calculating the synchronous stable value of the current period of the electric equipment according to the impedance voltage drop parameter of the current period of the electric equipment and the reactive compensation characteristic parameter of the current period of the electric equipment.
Optionally, the power operating parameters include a grid voltage amplitude and a terminal voltage rating of the power equipment, and the step of calculating the impedance drop parameter of the current cycle of the power equipment according to the power operating parameters of the current cycle of the power equipment includes:
calculating a generator terminal voltage vector of the electric equipment according to the voltage amplitude of the power grid and a generator terminal voltage rated value of the electric equipment;
decomposing a generator terminal voltage vector of the electric equipment into components in a quadrature axis direction;
and calculating the impedance voltage drop parameter of the current period of the electric equipment according to the quadrature component of the electric equipment.
Optionally, the wind energy data prediction model is obtained by:
acquiring sample historical productivity data of fan equipment and sample historical weather data of an area where a wind power plant is located, and performing normalization processing to obtain a first input characteristic sample;
acquiring a historical synchronous stable value of a sample of the electric power equipment, and performing normalization processing to obtain a second input characteristic sample;
training and cross-verifying a preset random forest model according to the first input characteristic sample and the second input characteristic sample to obtain a historical wind energy data prediction sequence of an initial wind energy data prediction model and a wind energy data prediction model;
and correcting the initial wind energy data prediction model according to the historical wind energy data prediction sequence of the wind energy data prediction model to obtain a target wind energy data prediction model.
Optionally, the step of modifying the initial wind energy data prediction model according to the historical wind energy data prediction sequence of the wind energy data prediction model comprises:
acquiring historical actual output wind energy data of a wind power plant;
calculating a historical actual output wind energy prediction error of the wind power plant according to the historical wind energy data prediction sequence and the historical actual output wind energy data;
and correcting the initial wind energy data prediction model according to the historical actual output wind energy prediction error of the wind power plant.
And modeling the historical actual output wind energy prediction error of the wind power plant based on the multivariate Gaussian distribution so as to realize the correction of the initial wind energy data prediction model.
Optionally, the step of modifying the initial wind energy data prediction model based on historical actual output wind energy prediction errors of the wind farm comprises:
and modeling the historical actual output wind energy prediction error of the wind power plant based on the multivariate Gaussian distribution so as to realize the correction of the initial wind energy data prediction model.
Optionally, after the step of modifying the initial wind energy data prediction model according to the historical wind energy data prediction sequence of the wind energy data prediction model to obtain the target wind energy data prediction model, the method further includes:
determining the lowest prediction error rate of the target wind energy data prediction model as the optimization direction of the first optimization function;
determining the maximum diversity index value of the target wind energy data prediction model as the optimization direction of the second optimization function;
and optimizing the target wind energy data prediction model according to the optimization direction of the first optimization function and the optimization direction of the second optimization function.
In a second aspect, an embodiment of the present invention provides a wind energy prediction system for a wind farm, the system including:
the wind turbine parameter acquisition module is used for acquiring historical productivity data of wind turbine equipment and estimated weather data of the next period of the region where the wind power plant is located;
the first characteristic construction module is used for constructing a first input characteristic according to historical productivity data of the fan equipment and estimated weather data of the next period of an area where the wind farm is located;
the electric power equipment parameter acquisition module is used for acquiring a synchronous stable value of the current period of the electric power equipment;
the second characteristic construction module is used for constructing a second input characteristic according to a synchronous stable value of the current period of the power equipment, wherein the synchronous stable value is used for representing the connection stable state of the power equipment and the wind power plant;
and the prediction module is used for inputting the first input characteristic and the second input characteristic into a wind energy data prediction model obtained by pre-training and outputting actual output wind energy prediction data of the next period of the wind power plant.
Optionally, the power equipment parameter acquisition module comprises:
the impedance voltage drop calculation submodule is used for calculating the impedance voltage drop parameter of the current period of the electric equipment according to the electric power operation parameter of the current period of the electric equipment;
the reactive compensation characteristic parameter calculation submodule is used for calculating the reactive compensation characteristic parameter of the current period of the electric equipment according to the influence capacity of the electric equipment on the fan equipment when the electric equipment executes reactive compensation;
and the synchronous stable value calculation submodule is used for calculating the synchronous stable value of the current period of the electric equipment according to the impedance voltage drop parameter of the current period of the electric equipment and the reactive compensation characteristic parameter of the current period of the electric equipment.
Optionally, the impedance-voltage drop calculation submodule includes:
the terminal voltage calculation unit is used for calculating a terminal voltage vector of the electric equipment according to the grid voltage amplitude and a terminal voltage rated value of the electric equipment by a vector;
the dividing unit is used for decomposing a generator terminal voltage vector of the electric equipment into components in a quadrature axis direction;
and the impedance voltage drop parameter calculation unit is used for calculating the impedance voltage drop parameter of the current period of the electric equipment according to the quadrature component of the electric equipment.
Optionally, the system further comprises a model training unit, and the model training module comprises:
the first characteristic obtaining submodule is used for obtaining sample historical productivity data of fan equipment and sample historical weather data of an area where a wind power plant is located, and conducting normalization processing to obtain a first input characteristic sample;
the second characteristic obtaining submodule is used for obtaining a historical synchronous stable value of the sample of the electric power equipment and conducting normalization processing to obtain a second input characteristic sample;
the training submodule is used for training and cross-verifying a preset random forest model according to the first input characteristic sample and the second input characteristic sample to obtain a historical wind energy data prediction sequence of an initial wind energy data prediction model and a wind energy data prediction model;
and the correction submodule is used for correcting the initial wind energy data prediction model according to the historical wind energy data prediction sequence of the wind energy data prediction model to obtain the target wind energy data prediction model.
Optionally, the modification submodule includes:
the acquiring unit is used for acquiring historical actual output wind energy data of the wind power plant;
the error determination unit is used for calculating the historical actual output wind energy prediction error of the wind power plant according to the historical wind energy data prediction sequence and the historical actual output wind energy data;
and the model correction unit is used for correcting the initial wind energy data prediction model according to the historical actual output wind energy prediction error of the wind power plant.
Optionally, the modification submodule further includes:
the first optimization unit is used for determining the lowest prediction error rate of the target wind energy data prediction model as the optimization direction of the first optimization function;
the second optimization unit is used for determining the diversity index value of the target wind energy data prediction model to be the highest as the optimization direction of the second optimization function;
and the model optimization unit is used for optimizing the target wind energy data prediction model according to the optimization direction of the first optimization function and the optimization direction of the second optimization function.
A third aspect of an embodiment of the present invention provides an electronic device, including a processor, a communication interface, a memory, and a communication bus, where the processor and the communication interface complete communication between the memory and the processor through the communication bus;
a memory for storing a computer program;
the processor is configured to implement the method steps set forth in the first aspect of the embodiment of the present invention when executing the program stored in the memory.
A fourth aspect of the embodiments of the present invention provides a computer-readable storage medium, on which a computer program is stored, which, when executed by a processor, implements the method as set forth in the first aspect of the embodiments of the present invention.
The embodiment of the invention has the following advantages: the method comprises the steps of firstly, obtaining historical capacity data of fan equipment and estimated weather data of a next period of an area where a wind power plant is located, constructing a first input characteristic according to the historical capacity data of the fan equipment and the estimated weather data of the next period of the area where the wind power plant is located, then obtaining a synchronous stable value of a current period of the power equipment, constructing a second input characteristic according to the synchronous stable value of the current period of the power equipment, and finally inputting the first input characteristic and the second input characteristic into a wind energy data prediction model obtained through pre-training and outputting actual output wind energy prediction data of the next period of the wind power plant. In the invention, the influence of the power equipment on the actual output electric energy of the wind power plant in the operation process is also used as a reference condition for predicting the actual output wind energy data of the wind power plant, so that the prediction result is more accurate, and enough electric energy reserved space can be provided for the normal operation of various equipment in the wind power plant.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
FIG. 1 is a flow chart illustrating the steps of a method for predicting wind energy in a wind farm in accordance with an embodiment of the present invention;
FIG. 2 is a block schematic diagram of a wind farm wind energy prediction system in an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, not all, embodiments of the present invention. All other embodiments, which can be obtained by a person skilled in the art without inventive step based on the embodiments of the present invention, are within the scope of protection of the present invention.
In the related art, most of the existing wind power plant wind energy prediction methods only predict the electric energy generated by a fan part in a wind power plant, but when the electric energy is actually transmitted to a power grid, loss occurs, the loss is used for maintaining the steady-state operation of various electric equipment in the wind power plant, and the loss dynamically changes along with the electric energy generated by the fan part, so that the influence of the electric equipment part is not considered in the existing wind power plant wind energy prediction methods, and the electric energy data transmitted to the power grid part can be predicted accurately. Based on the method, a brand-new wind power plant wind energy prediction method is provided.
Based on this, the inventor proposes the core technical concept of the application: the electric energy consumed by the electric equipment maintaining system in steady-state operation is also used as a reference condition for wind energy prediction of the power plant, so that a wind energy data prediction model with a stable value of the electric equipment is obtained, and multi-objective optimization is performed on the wind energy data prediction model from two aspects of model identification accuracy and model diversity, so that actual output wind energy prediction data can be more accurate.
The wind farm wind energy prediction method of the present application is explained below, and as shown in fig. 1, fig. 1 shows a flow chart of a wind farm wind energy prediction method of the present application.
Firstly, the wind energy data prediction model of the invention is obtained by the following steps:
s100-1: acquiring sample historical capacity data of fan equipment and sample historical weather data of an area where a wind power plant is located, and performing normalization processing to obtain a first input feature sample;
s100-2: acquiring a historical synchronous stable value of a sample of the electric power equipment, and performing normalization processing to obtain a second input characteristic sample;
s100-3: training and cross-verifying a preset random forest model according to the first input characteristic sample and the second input characteristic sample to obtain a historical wind energy data prediction sequence of an initial wind energy data prediction model and a wind energy data prediction model;
s100-4: and correcting the initial wind energy data prediction model according to the historical wind energy data prediction sequence of the wind energy data prediction model to obtain a target wind energy data prediction model.
In the implementation manner of steps S100-1 to S100-4, if a wind energy data prediction model of a wind farm is to be created, sample historical capacity data of a wind turbine device of the wind farm and sample historical weather data of an area where the wind farm is located need to be obtained, and a sample historical synchronization stable value of an electric power device.
As an example, if the sample historical capacity data of the wind turbine equipment is from 1 month to 5 months, and the sample holding time is four months, the input sample historical capacity data corresponding to the wind farm and the sample historical weather data of the area where the wind farm is located are acquired, and a training data set is formed through structured averaging for constructing a wind energy data prediction model of the wind farm for 6 months. The training data set comprises productivity data and weather data of a plurality of historical time period units, namely 1 month to 5 months, sample historical productivity data of 5 total time periods and sample historical weather data of a region where the wind power plant is located.
Training and cross-verifying a random forest model by using a first input characteristic sample consisting of sample historical capacity data of the normalized fan equipment, sample historical weather data of an area where a wind power plant is located and a second input characteristic sample consisting of a sample historical synchronous stable value of the power equipment to obtain an initial wind energy data prediction model and a historical wind energy data prediction sequence of the initial wind energy data prediction model predicted based on the initial wind energy data prediction model. And then correcting the initial wind energy data prediction model according to the historical wind energy data prediction sequence of the wind energy data prediction model, so as to obtain a final target wind energy data prediction model.
In one possible embodiment, the step of modifying the initial wind energy data prediction model comprises:
acquiring historical actual output wind energy data of a wind power plant;
calculating a historical actual output wind energy prediction error of the wind power plant according to the historical wind energy data prediction sequence and the historical actual output wind energy data;
and correcting the initial wind energy data prediction model according to the historical actual output wind energy prediction error of the wind power plant.
And modeling the historical actual output wind energy prediction error of the wind power plant based on the multivariate Gaussian distribution so as to realize the correction of the initial wind energy data prediction model.
In the embodiment, the historical actual output wind energy data of the wind power plant refers to wind energy data which are output to an external power grid and recorded in the wind power plant history, the actual sequence of the historical actual output wind energy data of the wind power plant is subtracted from the pre-measured sequence of the historical wind energy data, so that the historical actual output wind energy prediction error of the wind power plant is obtained, the error is modeled by using multivariate Gaussian distribution, and the joint probability distribution of the node on the electricity price prediction error is obtained. The probability distribution of the error sequence is modeled by using multivariate Gaussian distribution, the position parameters and covariance matrixes of the multivariate Gaussian distribution are estimated by using a maximum likelihood method, namely the joint probability distribution of the errors can be represented by the multivariate Gaussian distribution, and the correction of the initial wind energy data prediction model is realized based on the joint probability distribution.
In one possible embodiment, the step of modifying the initial wind energy data prediction model based on historical actual output wind energy prediction errors of the wind farm comprises:
and modeling the historical actual output wind energy prediction error of the wind power plant based on the multivariate Gaussian distribution so as to realize the correction of the initial wind energy data prediction model.
In a possible embodiment, after the step of modifying the initial wind energy data prediction model to obtain the target wind energy data prediction model according to the historical wind energy data prediction sequence of the wind energy data prediction model, the method further comprises:
determining the lowest prediction error rate of the target wind energy data prediction model as the optimization direction of a first optimization function;
determining the maximum diversity index value of the target wind energy data prediction model as the optimization direction of the second optimization function;
and optimizing the target wind energy data prediction model according to the optimization direction of the first optimization function and the optimization direction of the second optimization function.
In the present embodiment, after obtaining the target wind energy data prediction model, in order to further optimize the model, multi-objective optimization may be performed from two aspects of the prediction error rate of the wind energy data prediction model and the diversity index value of the target wind energy data prediction model. Firstly, an optimization algorithm of the optimization is determined, the optimization algorithm can select a second-generation non-inferior sequencing genetic evolution algorithm, the second-generation non-inferior sequencing genetic evolution algorithm has the advantage of better exploration performance, and in non-dominated sequencing, individuals close to the front edge of the pareto are selected, so that the pareto advancing capability is enhanced. In order to ensure that the prediction error rate of the target wind energy data prediction model is minimized, the prediction error rate of the target wind energy data prediction model is used as a first optimization function, the optimization direction is minimized, the scale factor is 0.2, and the weight is 1.0; in order to ensure that the diversity index value of the target wind energy data prediction model can be optimal, the diversity index value of the target wind energy data prediction model is used as a second optimization function, the optimization direction is maximized, the scale factor is 0.0002, and the weight r is 2.0. After parameters of the first optimization function and the second optimization function are determined, the target wind energy data prediction model is optimized according to the first optimization function and the second optimization function, a wind energy data prediction model meeting the multi-target optimization requirement is obtained, and after the wind energy data prediction model, a parameter solution set of the wind energy data prediction model can be determined according to the pareto domination relationship. And obtaining a parameter solution set of the wind energy data prediction model by eliminating pareto solutions with a dominated relation.
As an example, if it is found that a dominates B and D dominates C and there is no dominance relationship between a and D according to the fitness calculation result for the parameter solutions of the wind energy data prediction models numbered a, B, C, and D, B and C may be eliminated and a and D may be used as the parameter solutions of the wind energy data prediction models.
After the parameter solution set of the wind energy data prediction model is obtained, the solution with the best distributivity needs to be selected as the final model parameter of the wind energy data prediction model for solidification, and the sparsity of the parameter solution of each wind energy prediction model is determined by judging the number of the parameter solutions of other wind energy prediction models in the adjacent area of the parameter solution of the wind energy prediction model, wherein the smaller the number of the parameter solutions of other wind energy prediction models in the adjacent area is, the better the distributivity of the parameter solution of the wind energy prediction model is, and the larger the number of the parameter solutions of other wind energy prediction models in the adjacent area is, the worse the distributivity of the parameter solution of the wind energy prediction model is. And establishing a coordinate system by taking the prediction error rate of the wind energy data prediction model as a horizontal axis and the diversity index value of the wind energy data prediction model as a vertical axis. Under the coordinate system, the more the range of the circle corresponding to the parameter solution of the prediction model represents the more the parameter solutions of the niche range prediction model of the parameter solution of the wind energy prediction model in the coordinate system are, the lower the sparsity of the parameter solution of the prediction model is, and the worse the distributivity is. And after the parameters of the wind energy prediction model with the best distributivity are determined, the parameters are solidified, and the solidified target wind energy data prediction model is used for predicting actual output wind energy data of the next period of the wind power generation field.
After obtaining the target wind energy data prediction model, predicting actual output wind energy data of the next period of the wind power plant based on the target wind energy data prediction model, wherein the specific steps comprise:
s101: historical productivity data of the fan equipment and estimated weather data of the next period of the area where the wind power plant is located are obtained.
In the present embodiment, for a wind farm, the devices thereof can be mainly classified into two types, one type is a wind turbine device, i.e., a wind turbine generator set, for converting wind energy into electric energy, and the other type is electric equipment, such as a reactive power compensation device and the like. In a wind farm, however, the wind farm needs to provide a certain amount of dynamic reactive support to the grid during a fault, depending on the requirements of the grid. The reactive compensation speed of the reactive compensation device to the grid-connected point of the wind power plant is higher than that of the wind turbine generator, so that electric energy obtained by the wind turbine generator through wind power conversion is also required to be used for coordination and work of electric equipment in the wind power plant. Therefore, the electric energy actually output by the wind farm is not equal to the electric energy actually generated by the wind turbine equipment.
The historical productivity data of the fan equipment can be actual electric energy production data of the fan equipment in a previous time period, the time period can be in a month unit or a quarter unit, and the historical productivity data can be obtained through a report form issued by a production department. The estimated weather data can be a weather forecast of the region where the wind power plant is located, which is issued by the weather part.
For example, the historical productivity data of the fan device may be a production report of a first quarter of a certain wind farm, and the estimated weather data of the next period of the area where the wind farm is located may be a weather forecast of a certain area for several days in the future, which is issued by a television station.
In one possible embodiment, the predicted weather data includes at least one of a wind direction parameter, a wind speed parameter, a temperature parameter, a pressure parameter, and a humidity parameter.
In this embodiment, for wind power generation, the factor directly influencing the wind power generation is wind speed, and the wind speed can be determined according to a mapping relationship between any one parameter in the estimated weather data and the preset weather data and the wind speed data. The mapping relationship between the weather data and the wind speed data may be determined by a mapping relationship between the weather data and the nationwide average data of the wind speed data, or may be determined according to a mapping relationship between the actual weather data and the wind speed data in the region.
S102: and constructing a first input characteristic according to historical capacity data of the fan equipment and estimated weather data of the next period of the area where the wind farm is located.
In the embodiment, after obtaining the historical capacity data of the fan device and the estimated weather data of the next period of the area where the wind farm is located, the historical capacity data and the estimated weather data of the next period of the area where the wind farm is located need to be structured in units of time because the time units adopted by the wind farm are different, and the first input feature is constructed based on the processed data.
S103: and acquiring a synchronous stable value of the current period of the electric equipment, and constructing a second input characteristic according to the synchronous stable value of the current period of the electric equipment.
In the embodiment, the synchronous stability value is used for representing the connection stable state of the power equipment and the wind power plant, and the judgment of the synchronous stability margin is as follows: if the synchronous stability value is equal to 100%, the stable connection state of the electric power equipment and the wind power plant is the most stable state; if the connection stable state of the electric equipment and the wind power plant is equal to 0, the connection stable state of the electric equipment and the wind power plant is the most unstable state, so that the electric system of the wind power plant does not have any disturbance rejection capability. In actual production, the synchronous stability value is between 0 and 1, and the stability is higher when the synchronous stability value is larger.
And after the synchronous stable value of the current period of the electric equipment is obtained, the synchronous stable value is regulated, and a second input characteristic is constructed based on the processed data.
And the step of obtaining a synchronized steady value for the current cycle of the force equipment comprises:
s103-1: and calculating the impedance voltage drop parameter of the current period of the electric equipment according to the electric operation parameter of the current period of the electric equipment.
In this embodiment, the electric power operation parameter may be a grid voltage amplitude and a terminal voltage rating of the electric power equipment, and the step of determining the impedance drop parameter may be:
s103-1-1: calculating a generator terminal voltage vector of the electric equipment according to the voltage amplitude of the power grid and a generator terminal voltage rated value of the electric equipment;
s103-1-2: decomposing a generator terminal voltage vector of the electric equipment into components in a quadrature axis direction;
s103-1-3: and calculating the impedance voltage drop parameter of the current period of the electric equipment according to the quadrature component of the electric equipment.
In the embodiments of S103-1-1 to S103-1-3, the grid voltage amplitude may be obtained through offline equivalence calculation or online identification, the terminal voltage rated value of the electric power equipment may be obtained through data query provided by a station owner, a terminal voltage vector of the electric power equipment is calculated according to the grid voltage amplitude and the terminal voltage rated value of the electric power equipment, then the terminal voltage vector of the electric power equipment is decomposed into a direct-axis component and a quadrature-axis component in a phase-locked loop coordinate system, and finally, the impedance drop parameter of the electric power equipment in the current period is calculated according to the quadrature-axis component of the electric power equipment. The smaller the impedance voltage drop is, the better the synchronization between the electric equipment and the power grid is, and because of the impedance voltage drop, the terminal voltage is influenced to a certain degree, so that the synchronization stability of the electric equipment is influenced.
S103-2: calculating reactive compensation characteristic parameters of the current period of the electric equipment according to the influence capacity of the electric equipment on the fan equipment when the electric equipment executes reactive compensation;
s103-3: and calculating the synchronous stable value of the current period of the electric equipment according to the impedance voltage drop parameter of the current period of the electric equipment and the reactive compensation characteristic parameter of the current period of the electric equipment.
In the implementation modes from S103-2 to S103-3, the reactive compensation characteristic parameters are used for representing the transient fault ride-through capability of the wind power plant, a wind power plant reactive optimization function is constructed in the method, and the working point with the least reactive capacity use of the centralized reactive compensation device is obtained by solving the wind power plant reactive optimization function on line
And after the impedance voltage drop parameter of the electric power equipment in the current period and the reactive compensation characteristic parameter of the electric power equipment in the current period are obtained, the synchronous stable value of the electric power equipment in the current period can be obtained according to a calculation formula of the synchronous stable value.
S104: and inputting the first input characteristic and the second input characteristic into a wind energy data prediction model obtained by pre-training, and outputting actual output wind energy prediction data of the next period of the wind power plant.
In the embodiment, after the first input characteristic and the second input characteristic of the wind power plant are constructed, the actual output wind energy prediction data of the next period of the wind power plant according to the first input characteristic and the second input characteristic are needed, namely, the electric energy for the steady state of the power system maintenance system is subtracted from the electric energy generated,
therefore, the first input characteristic and the second input characteristic are input into a wind energy data prediction model which is trained in advance, so that the predicted actual output wind energy data of the wind power plant in the next period is obtained, and the predicted electricity price is short-term predicted data.
According to the method, historical productivity data of the fan equipment and estimated weather data of a next period of an area where a wind power plant is located are obtained, a first input feature is constructed according to the historical productivity data of the fan equipment and the estimated weather data of the next period of the area where the wind power plant is located, then a synchronous stable value of a current period of the power equipment is obtained, a second input feature is constructed according to the synchronous stable value of the current period of the power equipment, and finally the first input feature and the second input feature are input into a wind energy data prediction model obtained through pre-training and output to obtain actual output wind energy prediction data of the next period of the wind power plant. In the invention, the influence of the power equipment on the actual output electric energy of the wind power plant in the operation process is also used as a reference condition for predicting the actual output wind energy data of the wind power plant, so that the prediction result is more accurate, and enough electric energy reserved space can be provided for the normal operation of various equipment in the wind power plant. And the dynamic reactive power supporting capability of the wind power plant at the fault stage can be improved, the voltage of the wind turbine generator terminal can be maintained in a reasonable operation interval, and the operation safety of the wind turbine generator is ensured.
An embodiment of the present invention further provides a wind power plant wind energy prediction system, and referring to fig. 2, a functional block diagram of a first aspect of an embodiment of a wind power plant wind energy prediction system of the present invention is shown, the system includes:
the wind turbine parameter obtaining module 201 is configured to obtain historical productivity data of the wind turbine device and estimated weather data of a next period of an area where the wind farm is located;
the first characteristic construction module 202 is used for constructing a first input characteristic according to historical productivity data of the fan equipment and estimated weather data of the next period of an area where the wind farm is located;
the electric power equipment parameter obtaining module 203 is used for obtaining a synchronous stable value of the current period of the electric power equipment;
a second feature construction module 204, configured to construct a second input feature according to a synchronous stable value of the current period of the power equipment, where the synchronous stable value is used to represent a connection stable state of the power equipment and the wind farm;
and the prediction module 205 is configured to input the first input feature and the second input feature into a wind energy data prediction model obtained through pre-training, and output actual output wind energy prediction data obtained in a next period of the wind power plant.
In one possible embodiment, the power equipment parameter obtaining module includes:
the impedance voltage drop calculation submodule is used for calculating the impedance voltage drop parameter of the current period of the electric equipment according to the electric power operation parameter of the current period of the electric equipment;
the reactive compensation characteristic parameter calculation submodule is used for calculating the reactive compensation characteristic parameter of the current period of the electric equipment according to the influence capacity of the electric equipment on the fan equipment when the electric equipment executes reactive compensation;
and the synchronous stable value calculation submodule is used for calculating the synchronous stable value of the current period of the electric equipment according to the impedance voltage drop parameter of the current period of the electric equipment and the reactive compensation characteristic parameter of the current period of the electric equipment.
In one possible embodiment, the impedance drop calculation submodule includes:
the terminal voltage calculation unit is used for calculating a terminal voltage vector of the electric equipment according to the grid voltage amplitude and a terminal voltage rated value of the electric equipment by a vector;
the dividing unit is used for decomposing a generator terminal voltage vector of the electric equipment into components in a quadrature axis direction;
and the impedance voltage drop parameter calculation unit is used for calculating the impedance voltage drop parameter of the current period of the electric equipment according to the quadrature component of the electric equipment.
In one possible embodiment, the system further comprises a model training unit, and the model training module comprises:
the first characteristic obtaining submodule is used for obtaining sample historical productivity data of fan equipment and sample historical weather data of an area where a wind power plant is located, and conducting normalization processing to obtain a first input characteristic sample;
the second characteristic obtaining submodule is used for obtaining a historical synchronous stable value of the sample of the electric power equipment and conducting normalization processing to obtain a second input characteristic sample;
the training submodule is used for training and cross-verifying a preset random forest model according to the first input characteristic sample and the second input characteristic sample to obtain a historical wind energy data prediction sequence of an initial wind energy data prediction model and a wind energy data prediction model;
and the correction submodule is used for correcting the initial wind energy data prediction model according to the historical wind energy data prediction sequence of the wind energy data prediction model to obtain a target wind energy data prediction model.
In one possible embodiment, the correction submodule includes:
the acquiring unit is used for acquiring historical actual output wind energy data of the wind power plant;
the error determination unit is used for calculating the historical actual output wind energy prediction error of the wind power plant according to the historical wind energy data prediction sequence and the historical actual output wind energy data;
and the model correction unit is used for correcting the initial wind energy data prediction model according to the historical actual output wind energy prediction error of the wind power plant.
In a possible embodiment, the first optimization unit is used for determining the lowest prediction error rate of the target wind energy data prediction model as the optimization direction of the first optimization function;
the second optimization unit is used for determining the diversity index value of the target wind energy data prediction model to be the highest as the optimization direction of the second optimization function;
and the model optimization unit is used for optimizing the target wind energy data prediction model according to the optimization direction of the first optimization function and the optimization direction of the second optimization function.
Based on the same inventive concept, an embodiment of the present application further provides an electronic device, including:
at least one processor; and a memory communicatively coupled to the at least one processor; wherein the memory stores instructions executable by the at least one processor to cause the at least one processor to perform the wind farm wind energy prediction method of embodiments of the present application.
In addition, to achieve the above object, an embodiment of the present application further proposes a computer readable storage medium storing a computer program, which when executed by a processor implements the wind farm wind energy prediction method of the embodiment of the present application.
As will be appreciated by one of skill in the art, embodiments of the present invention may be provided as a method, apparatus, or computer program product. Accordingly, embodiments of the present invention may take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, embodiments of the present invention may take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, and the like) having computer-usable program code embodied therein.
Embodiments of the present invention are described with reference to flowchart illustrations and/or block diagrams of methods, terminal devices (apparatus), and computer program products according to embodiments of the invention. It will be understood that each flow and/or block of the flow diagrams and/or block diagrams, and combinations of flows and/or blocks in the flow diagrams and/or block diagrams, can be implemented by computer program instructions. These computer program instructions may be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing terminal to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing terminal, create means for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be stored in a computer-readable memory that can direct a computer or other programmable data processing terminal to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instruction means which implement the function specified in the flowchart flow or flows and/or block diagram block or blocks.
These computer program instructions may also be loaded onto a computer or other programmable data processing terminal to cause a series of operational steps to be performed on the computer or other programmable terminal to produce a computer implemented process such that the instructions which execute on the computer or other programmable terminal provide steps for implementing the functions specified in the flowchart flow or flows and/or block diagram block or blocks.
Finally, it should also be noted that, in this document, relational terms such as first and second, and the like are used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. "and/or" means that either or both of them can be selected. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or terminal that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or terminal. Without further limitation, an element defined by the phrases "comprising one of 8230; \8230;" 8230; "does not exclude the presence of additional like elements in a process, method, article, or terminal device that comprises the element.
The wind power plant wind energy prediction method and system provided by the invention are described in detail, and the principle and the implementation mode of the invention are explained by applying specific examples, and the description of the examples is only used for helping to understand the method and the core idea of the invention; meanwhile, for a person skilled in the art, according to the idea of the present invention, the specific embodiments and the application range may be changed, and in summary, the content of the present specification should not be construed as a limitation to the present invention.
Claims (10)
1. A method of predicting wind energy in a wind farm, the method comprising:
obtaining historical productivity data of fan equipment and estimated weather data of the next period of an area where a wind power plant is located;
constructing a first input characteristic according to historical productivity data of the fan equipment and estimated weather data of the next period of the region where the wind power plant is located;
acquiring a synchronous stable value of the current period of the electric power equipment, and constructing a second input characteristic according to the synchronous stable value of the current period of the electric power equipment, wherein the synchronous stable value is used for representing a connection stable state of the electric power equipment and the wind power plant;
and inputting the first input characteristic and the second input characteristic into a wind energy data prediction model obtained by pre-training, and outputting to obtain actual output wind energy prediction data of the next period of the wind power plant.
2. The method of wind farm wind energy prediction according to claim 1, characterized in that the step of obtaining a synchronous steady value of the current period of the electric power equipment comprises:
calculating an impedance voltage drop parameter of the current period of the electric equipment according to the electric power operation parameter of the current period of the electric equipment;
calculating reactive compensation characteristic parameters of the current period of the electric equipment according to the influence capacity of the electric equipment on the fan equipment when the electric equipment executes reactive compensation;
and calculating the synchronous stable value of the current period of the electric equipment according to the impedance voltage drop parameter of the current period of the electric equipment and the reactive compensation characteristic parameter of the current period of the electric equipment.
3. The method for wind power plant wind energy prediction according to claim 2, characterized in that said electric operating parameters comprise a grid voltage amplitude and a terminal voltage rating of said electric equipment, and the step of calculating an impedance drop parameter for a current cycle of said electric equipment from said electric operating parameters for said current cycle of said electric equipment comprises:
calculating a generator end voltage vector of the electric equipment according to the grid voltage amplitude and a generator end voltage rated value of the electric equipment;
decomposing a generator terminal voltage vector of the electric equipment into components in a quadrature axis direction;
and calculating the impedance voltage drop parameter of the current period of the electric equipment according to the quadrature component of the electric equipment.
4. The wind farm wind energy prediction method according to claim 1, characterized in that the wind energy data prediction model is obtained by:
obtaining sample historical capacity data of the fan equipment and sample historical weather data of an area where the wind power plant is located, and conducting normalization processing to obtain a first input feature sample;
acquiring a historical synchronous stable value of the sample of the electric power equipment, and performing normalization processing to obtain a second input characteristic sample;
training and cross-verifying a preset random forest model according to the first input feature sample and the second input feature sample to obtain historical wind energy data prediction sequences of the initial wind energy data prediction model and the wind energy data prediction model;
and correcting the initial wind energy data prediction model according to the historical wind energy data prediction sequence of the wind energy data prediction model to obtain a target wind energy data prediction model.
5. The wind farm wind energy prediction method according to claim 4, wherein the step of modifying the initial wind energy data prediction model based on a historical wind energy data prediction sequence of the wind energy data prediction model comprises:
acquiring historical actual output wind energy data of a wind power plant;
calculating a historical actual output wind energy prediction error of the wind power plant according to the historical wind energy data prediction sequence and the historical actual output wind energy data;
and correcting the initial wind energy data prediction model according to the historical actual output wind energy prediction error of the wind power plant.
6. The method of wind power plant wind energy prediction according to claim 5, characterized in that said step of revising said initial wind energy data prediction model based on historical actual output wind energy prediction errors of said wind power plant comprises:
and modeling the historical actual output wind energy prediction error of the wind power plant based on the multivariate Gaussian distribution so as to realize the correction of the initial wind energy data prediction model.
7. The wind farm wind energy prediction method of claim 4, wherein after the step of modifying the initial wind energy data prediction model to obtain a target wind energy data prediction model based on a historical wind energy data prediction sequence of the wind energy data prediction model, the method further comprises:
determining the lowest prediction error rate of the target wind energy data prediction model as the optimization direction of a first optimization function;
determining the maximum diversity index value of the target wind energy data prediction model as the optimization direction of the second optimization function;
and optimizing the target wind energy data prediction model according to the optimization direction of the first optimization function and the optimization direction of the second optimization function.
8. A wind farm wind energy prediction system, characterized in that the system comprises:
the wind turbine parameter acquisition module is used for acquiring historical productivity data of wind turbine equipment and estimated weather data of the next period of the region where the wind power plant is located;
the first characteristic construction module is used for constructing a first input characteristic according to historical productivity data of the fan equipment and estimated weather data of the next period of the region where the wind power plant is located;
the electric power equipment parameter acquisition module is used for acquiring a synchronous stable value of the current period of the electric power equipment;
the second characteristic construction module is used for constructing a second input characteristic according to a synchronous stable value of the current period of the electric power equipment, wherein the synchronous stable value is used for representing the connection stable state of the electric power equipment and the wind power plant;
and the prediction module is used for inputting the first input characteristic and the second input characteristic into a wind energy data prediction model obtained by pre-training and outputting actual output wind energy prediction data of the next period of the wind power plant.
9. The wind farm wind energy prediction system of claim 8, wherein the power equipment parameter acquisition module comprises:
the impedance voltage drop calculation submodule is used for calculating the impedance voltage drop parameter of the current period of the electric equipment according to the electric operation parameter of the current period of the electric equipment;
the reactive compensation characteristic parameter calculation submodule is used for calculating reactive compensation characteristic parameters of the current period of the electric power equipment according to the influence capacity of the electric power equipment on the fan equipment when the electric power equipment executes reactive compensation;
and the synchronous stable value calculation submodule is used for calculating the synchronous stable value of the current period of the electric equipment according to the impedance voltage drop parameter of the current period of the electric equipment and the reactive compensation characteristic parameter of the current period of the electric equipment.
10. The wind farm wind energy prediction system of claim 8, wherein the impedance voltage drop calculation sub-module comprises:
the generator end voltage calculation unit is used for calculating a generator end voltage vector of the electric equipment according to the grid voltage amplitude and a generator end voltage rated value of the electric equipment by a vector;
the dividing unit is used for decomposing a generator terminal voltage vector of the electric equipment into components in a quadrature axis direction;
and the impedance voltage drop parameter calculation unit is used for calculating the impedance voltage drop parameter of the current period of the electric equipment according to the quadrature component of the electric equipment.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211607577.XA CN115936924B (en) | 2022-12-14 | 2022-12-14 | Wind energy prediction method and system for wind power plant |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211607577.XA CN115936924B (en) | 2022-12-14 | 2022-12-14 | Wind energy prediction method and system for wind power plant |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115936924A true CN115936924A (en) | 2023-04-07 |
| CN115936924B CN115936924B (en) | 2023-08-25 |
Family
ID=86553682
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211607577.XA Active CN115936924B (en) | 2022-12-14 | 2022-12-14 | Wind energy prediction method and system for wind power plant |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115936924B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102842105A (en) * | 2012-07-09 | 2012-12-26 | 中国电力科学研究院 | Online transient state stability risk evaluating method for metering wind power uncertainty |
| CN103996087A (en) * | 2014-06-09 | 2014-08-20 | 北京东润环能科技股份有限公司 | Method and system for forecasting new energy power generation power |
| US20190280481A1 (en) * | 2016-10-20 | 2019-09-12 | Hitachi, Ltd. | Voltage/reactive power operation assisting device and assisting method, and voltage/reactive power operation monitoring control device and monitoring control method |
| US20200200145A1 (en) * | 2017-06-07 | 2020-06-25 | Vestas Wind Systems A/S | Adaptive estimation of available power for wind turbine |
| CN113361761A (en) * | 2021-06-01 | 2021-09-07 | 山东大学 | Short-term wind power integration prediction method and system based on error correction |
| WO2022033258A1 (en) * | 2020-08-14 | 2022-02-17 | 中国科学院分子细胞科学卓越创新中心 | Method and system for multi-step prediction of future wind speed based on automatic reservoir neural network |
| CN114418180A (en) * | 2021-12-16 | 2022-04-29 | 广东电网有限责任公司 | Ultra-short-term prediction method and device for wind power and storage medium |
| CN114465244A (en) * | 2021-12-24 | 2022-05-10 | 国电南瑞科技股份有限公司 | Large wind farm reactive voltage control method and device considering voltage regulation margin |
| CN114726009A (en) * | 2022-06-09 | 2022-07-08 | 东南大学溧阳研究院 | Wind power plant group reactive power hierarchical optimization control method and system considering power prediction |
| CN115081742A (en) * | 2022-07-22 | 2022-09-20 | 北京东润环能科技股份有限公司 | Ultra-short-term power prediction method for distributed wind power plant and related equipment |
-
2022
- 2022-12-14 CN CN202211607577.XA patent/CN115936924B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102842105A (en) * | 2012-07-09 | 2012-12-26 | 中国电力科学研究院 | Online transient state stability risk evaluating method for metering wind power uncertainty |
| CN103996087A (en) * | 2014-06-09 | 2014-08-20 | 北京东润环能科技股份有限公司 | Method and system for forecasting new energy power generation power |
| US20190280481A1 (en) * | 2016-10-20 | 2019-09-12 | Hitachi, Ltd. | Voltage/reactive power operation assisting device and assisting method, and voltage/reactive power operation monitoring control device and monitoring control method |
| US20200200145A1 (en) * | 2017-06-07 | 2020-06-25 | Vestas Wind Systems A/S | Adaptive estimation of available power for wind turbine |
| WO2022033258A1 (en) * | 2020-08-14 | 2022-02-17 | 中国科学院分子细胞科学卓越创新中心 | Method and system for multi-step prediction of future wind speed based on automatic reservoir neural network |
| CN113361761A (en) * | 2021-06-01 | 2021-09-07 | 山东大学 | Short-term wind power integration prediction method and system based on error correction |
| CN114418180A (en) * | 2021-12-16 | 2022-04-29 | 广东电网有限责任公司 | Ultra-short-term prediction method and device for wind power and storage medium |
| CN114465244A (en) * | 2021-12-24 | 2022-05-10 | 国电南瑞科技股份有限公司 | Large wind farm reactive voltage control method and device considering voltage regulation margin |
| CN114726009A (en) * | 2022-06-09 | 2022-07-08 | 东南大学溧阳研究院 | Wind power plant group reactive power hierarchical optimization control method and system considering power prediction |
| CN115081742A (en) * | 2022-07-22 | 2022-09-20 | 北京东润环能科技股份有限公司 | Ultra-short-term power prediction method for distributed wind power plant and related equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115936924B (en) | 2023-08-25 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Preece et al. | Efficient estimation of the probability of small-disturbance instability of large uncertain power systems | |
| CN105790265B (en) | A kind of uncertain Unit Combination model and method for solving considering AC power flow constraint | |
| Torbaghan et al. | A market-based transmission planning for HVDC grid—case study of the North Sea | |
| Wu et al. | Two-stage stochastic dual dynamic programming for transmission expansion planning with significant renewable generation and Nk criterion | |
| Kamarposhti et al. | Effect of wind penetration and transmission line development in order to reliability and economic cost on the transmission system connected to the wind power plant | |
| CN110264110B (en) | Energy storage power station site selection and volume fixing method based on multiple application scenes of power distribution network | |
| CN110867852A (en) | Microgrid energy storage optimization configuration method and device considering whole life cycle cost | |
| CN112787329A (en) | Optimal power flow calculation method containing wind power access based on robust cone planning | |
| CN112994011B (en) | Multi-source power system day-ahead optimal scheduling method considering voltage risk constraint | |
| CN111525590A (en) | Dynamic reactive power compensation device modeling method and device | |
| CN111756031B (en) | Power grid operation trend estimation method and system | |
| CN115936924B (en) | Wind energy prediction method and system for wind power plant | |
| CN115566680B (en) | New energy power system time sequence production simulation operation optimization method and device | |
| CN116995740A (en) | Distributed wind power and energy storage optimal configuration method and system for power distribution network | |
| CN116865318A (en) | Power transmission network and energy storage joint planning method and system based on two-stage random optimization | |
| CN113723717B (en) | Method, device, equipment and readable storage medium for predicting short-term load before system day | |
| CN114726090A (en) | Online splicing method and system for medium and low voltage network data based on power flow adjustment | |
| CN111553398B (en) | Wind power scene uncertain continuous interval obtaining method based on multidimensional normal distribution | |
| CN114330865A (en) | Power grid reserve capacity prediction method and system, computer equipment and storage medium | |
| CN112803498A (en) | Real-time scheduling method and system for active-reactive coordination under uncertain probability distribution | |
| Liu et al. | A novel acceleration strategy for nl contingency screening in distribution system | |
| Lilja et al. | Computing Equivalent hydropower models in Sweden using inflow clustering | |
| Zhang et al. | Robust unit commitment considering the temporal and spatial correlations of wind farms using a data-adaptive approach | |
| Jiang et al. | Security-constrained unit commitment with flexible uncertainty set for wind power generation | |
| CN117791715B (en) | Optimal configuration method and system for distributed photovoltaic power generation |
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 |