CN108171363B - Method and device for predicting photo-thermal power generation power - Google Patents

Abstract

Embodiments of the present invention provide a method and device for predicting CSP power. The method for predicting CSP power includes: predicting the temperature of the heat transfer medium according to meteorological data and heliostat control parameters; predicting the temperature of the heat transfer medium and the flow rate of the heat transfer medium, predicting the generating power. The method and device for predicting the power of photothermal power generation provided by the present invention can predict the temperature of the heat transfer medium according to the meteorological data and the control parameters of the heliostat for the photothermal conversion link, so as to realize the conversion of light energy into thermal energy in the photothermal conversion link. Prediction. For the turbine power generation link, according to the temperature of the heat transfer medium and the flow rate of the heat transfer medium, the power generation of the CSP system is predicted, and the prediction of the thermal energy converted into electrical energy in the turbine power generation link is realized. In conclusion, the method and device for predicting the CSP power provided by the present invention can more accurately predict the CSP power generation system.

Description

Method and device for predicting power of solar thermal power generation

technical field

The embodiments of the present invention relate to the technical field of solar thermal power generation, and in particular, to a method and device for predicting the power of solar thermal power generation.

Background technique

Solar thermal power generation refers to the use of large-scale arrays of parabolic or dish-shaped mirrors to collect solar thermal energy, provide steam through heat exchange devices, and combine the technology of traditional steam turbine generators to achieve the purpose of generating electricity. The principle is that the sunlight is concentrated to the solar collector device through the reflector, the heat transfer medium in the collector device is heated by the solar energy, and the water is added to form steam to drive or directly drive the generator to generate electricity. Compared with photovoltaic power generation systems and wind power generation systems, the solar thermal power generation system is a rather complex system, with a wide variety of equipment, high cost and difficult control.

Tower type solar thermal power generation, also known as concentrated solar thermal power generation, is in the form of using a certain number of reflector arrays to reflect solar radiation to the solar receiver placed at the top of the tower, and generate superheated steam by heating the working medium. Drive the steam turbine generator set to generate electricity, thereby converting the absorbed solar energy into electricity.

The tower CSP system includes multiple links such as solar concentration, light-to-heat conversion, heat transfer, heat storage, and turbine power generation. Existing tower CSP projects aim at the normal operation of the system, assemble the equipment in each link, and only make a rough estimate of the power generation based on experience, without predicting the system performance. In the process of grid-connected power generation, in order to facilitate planning and scheduling control, it is particularly important to accurately predict the power generation of the system.

SUMMARY OF THE INVENTION

Embodiments of the present invention provide a method and device for predicting the power of a solar thermal power generation system, so as to more accurately predict the power generation of a solar thermal power generation system.

To achieve the above object, the present invention adopts the following technical solutions:

In one aspect, the present invention provides a method for predicting CSP power, comprising: predicting the temperature of a heat transfer medium according to meteorological data and heliostat control parameters; flow, and predict the power generation of the CSP system.

On the other hand, the present invention also provides a CSP power prediction device, comprising: a first prediction module for predicting the temperature of the heat transfer medium according to meteorological data and heliostat control parameters; a second prediction module for using The power generation of the solar thermal power generation system is predicted based on the temperature of the heat transfer medium and the flow rate of the heat transfer medium.

The method and device for predicting the power of photothermal power generation provided by the present invention can predict the temperature of the heat transfer medium according to the meteorological data and the control parameters of the heliostat for the photothermal conversion link, so as to realize the conversion of light energy into thermal energy in the photothermal conversion link. Prediction. For the turbine power generation link, according to the temperature of the heat transfer medium and the flow rate of the heat transfer medium, the power generation of the CSP system is predicted, and the prediction of the thermal energy converted into electrical energy in the turbine power generation link is realized. In conclusion, the method and device for predicting the CSP power provided by the present invention can more accurately predict the CSP power generation system.

The above description is only an overview of the technical solutions of the present invention, in order to be able to understand the technical means of the present invention more clearly, it can be implemented according to the content of the description, and in order to make the above and other purposes, features and advantages of the present invention more obvious and easy to understand , the following specific embodiments of the present invention are given.

Description of drawings

Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are for the purpose of illustrating preferred embodiments only and are not to be considered limiting of the invention. Also, the same components are denoted by the same reference numerals throughout the drawings. In the attached image:

Fig. 1 is the structural schematic diagram of tower type solar thermal power generation system;

2 is a schematic flowchart of an embodiment of a method for predicting CSP power provided by the present invention;

3 is a schematic flowchart of another embodiment of a method for predicting CSP power provided by the present invention;

4 is a schematic diagram of the working principle of the training and prediction process of the support vector machine SVM numerical model;

FIG. 5 is a schematic structural diagram of an embodiment of the device for predicting CSP power provided by the present invention.

Detailed ways

Exemplary embodiments of the present disclosure will be described in more detail below with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be embodied in various forms and should not be limited by the embodiments set forth herein. Rather, these embodiments are provided so that the present disclosure will be more thoroughly understood, and will fully convey the scope of the present disclosure to those skilled in the art.

The method and device for predicting CSP power according to the embodiment of the present invention are aimed at a tower type CSP system. The thermal power generation system will be explained. Figure 1 is a schematic diagram of the structure of a tower CSP system. As shown in Figure 1, the sunlight emitted by the sun is reflected by a heliostat and then received by a solar receiver placed at the top of the tower. By heating the heat transfer medium, the The superheated steam is generated to drive the turbine generator to generate electricity and input to the grid, thereby converting the absorbed solar energy into electricity.

The embodiment of the present invention adopts the support vector machine SVM numerical model for prediction respectively for the photothermal conversion link and the turbine power generation link in the tower solar thermal power generation system, and obtains the predicted value of the power generation of the solar thermal power generation system. Support vector machine (SVM) algorithm is a supervised learning model and related learning algorithm for analyzing data in classification and regression analysis. Given a set of training instances, each labeled as belonging to one or the other of two classes, the SVM training algorithm creates a model that assigns new instances to one of the two classes, making it A non-probabilistic binary linear classifier. The Support Vector Machine (SVM) model represents instances as points in space such that the mapping makes instances of individual classes separated by as wide a noticeable interval as possible. Then, map the new instances to the same space and predict the class they belong to based on which side of the interval they fall on. Support vector machines construct hyperplanes or sets of hyperplanes in a high- or infinite-dimensional space, which can be used for classification, regression, or other tasks.

The method and device for predicting CSP power according to embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

Example 1

FIG. 2 is a schematic flowchart of an embodiment of a method for predicting CSP power provided by the present invention. As shown in FIG. 2 , the method for predicting CSP power according to the embodiment of the present invention may specifically include the following steps:

S201, predicting the temperature of the heat transfer medium according to the meteorological data and the control parameters of the heliostat.

Specifically, in this step, for the light-to-heat conversion link, how to accurately calculate the heat of the heat transfer medium converted from the gathered light energy is given. Specifically, it can be realized by predicting the temperature of the heat transfer medium according to meteorological data and heliostat control parameters.

S202 , predict the power generation of the solar thermal power generation system according to the temperature of the heat transfer medium and the flow rate of the heat transfer medium.

Specifically, this step provides how to accurately calculate the electric energy converted from the heat of the heat transfer medium for the turbine power generation link. Specifically, it can be realized by predicting the power generation of the solar thermal power generation system according to the predicted temperature of the heat transfer medium and the obtained flow rate of the heat transfer medium.

It should be noted here that, in the method for predicting CSP power in the embodiment of the present invention, the time lag and heat dissipation loss of the heat transfer and storage link are ignored, that is, the temperature of the heat transfer medium output from the tower section is equal to the heat transfer medium at the turbine end. , that is, the temperature of the heat transfer medium in the embodiment of the present invention is equal to the temperature of the heat transfer medium output from the tower section, and is also equal to the temperature of the heat transfer medium at the turbine end.

The method for predicting the power of CSP according to the embodiment of the present invention predicts the temperature of the heat transfer medium according to the meteorological data and the control parameters of the heliostat for the light-to-heat conversion link, so as to realize the prediction of the heat energy converted from the light energy by the light-to-heat conversion link. predict. For the turbine power generation link, according to the temperature of the heat transfer medium and the flow rate of the heat transfer medium, the power generation of the CSP system is predicted, and the prediction of the thermal energy converted into electrical energy in the turbine power generation link is realized. To sum up, the method for predicting the CSP power of the embodiment of the present invention can more accurately predict the power generation of the CSP system.

Embodiment 2

FIG. 3 is a schematic flowchart of another embodiment of the method for predicting CSP power provided by the present invention. The method for predicting CSP power in the embodiment of the present invention is a specific implementation of the method for predicting CSP power in the embodiment shown in FIG. 2 . As shown in FIG. 3 , the method for predicting CSP power according to the embodiment of the present invention may specifically include the following steps:

Step S201 in the embodiment shown in FIG. 2 may specifically include the following steps: predicting the temperature of the heat transfer medium based on a photothermal numerical model according to meteorological data and heliostat control parameters.

Specifically, for the light-to-heat conversion link, the temperature of the heat transfer medium is predicted according to meteorological data and heliostat control parameters. Specifically, a specific calculation formula or a light-to-heat numerical model obtained by machine learning training can be used for prediction. The photothermal numerical model may specifically be a Support Vector Machine (SVM for short) numerical model.

Further, based on the photothermal numerical model, step S201 may specifically include the following steps S301 and S302.

S301 , using historical data of meteorological data and historical data of control parameters of the heliostat as input, and using historical data of temperature of the heat transfer medium as output, train to obtain a photothermal numerical model.

Specifically, this step is the training process of the photothermal numerical model of the photothermal conversion link. The historical data of meteorological data and the historical data of heliostat control parameters are used as the input of the photothermal numerical model of the photothermal conversion link, and the historical data of the temperature of the heat transfer medium is used as the output of the photothermal numerical model of the photothermal conversion link. Using numerical algorithms such as support vector machine SVM algorithm, the optical-thermal numerical model of the optical-thermal conversion link is obtained by training.

S302 , taking the predicted value of the meteorological data and the predicted value of the control parameters of the heliostat as input, and based on the photothermal numerical model, obtain the predicted value of the temperature of the output heat transfer medium.

Specifically, this step is the prediction process of the photothermal numerical model of the photothermal conversion link. The predicted value of meteorological data (derived from the weather forecast) and the predicted value of the heliostat control parameters (derived from the control system) are used as the input of the optical-thermal numerical model of the optical-thermal conversion link. The photothermal numerical model is used for prediction, and the predicted value of the temperature of the heat transfer medium output by the photothermal numerical model of the photothermal conversion link is obtained.

Support vector machine SVM includes support vector classification machine (support vector classification, SVC for short) and support vector regression (support vector regression, SVR for short), both of which are divided into linear and nonlinear problems. The present invention adopts support vector regression machine SVR for modeling. For a given training sample set {(x ₁ ,y ₁ ),(x ₂ ,y ₂ ),…,(x ₃ ,y ₃ )}, where x _i ∈ R ⁿ , i.e. meteorological data, heliostat control The historical data of the parameters is in a two-dimensional array format; y _i ∈ R, the historical data of the temperature of the heat transfer medium, is in a one-dimensional array format; i=1, 2, 3..., a simple linear regression function can be expressed as :

f(x)=w*x+b(1)

In formula (1), w is the weight coefficient or weight, and b is the bias. For nonlinear regression problems, the basic idea of SVM is to transform the input space into a high-dimensional space with the nonlinear transformation defined by the inner product function. Find nonlinear relationships between input and output variables in a high-dimensional space:

f(x)=w·Φ(x)+b(2)

In formula (2), Φ(x) is the nonlinear transformation from the input space to the high-dimensional space.

In the conventional SVM algorithm, this low-dimensional to high-dimensional transformation is achieved through a kernel function. Commonly used kernel functions are:

Linear kernel function: k(u,v)=(u·v)

Polynomial kernel function: k(u,v)=(r(u·v)+coef0) ^d

RBF kernel function: k(u,v)=exp(-r|uv| ² )

Sigmoid kernel function: k(u,v)=tanh(r(u-v)+coef0)

Among them, the linear kernel function is mainly used in the case of linear separability, which is not suitable for the present invention, and the present invention discusses nonlinear problems. The case where the polynomial kernel function can be used is a relatively simple nonlinear case, which is difficult to use in a complex case, so it is not suitable for the present invention. The RBF kernel function can be used in various situations. The RBF kernel function is the most widely used kernel function, has good properties, and shows good performance in practical problems. Therefore, the present invention can use the commonly used RBF kernel function to achieve Low-dimensional to high-dimensional transformation.

Through the above process, a support vector machine SVM numerical model can be established between meteorological data, heliostat control parameters, and the temperature of the heat transfer medium, and then the actual historical data is substituted into this model, and the SVM algorithm is trained and learned through the support vector machine. Get a numerical matrix of weights w and biases b. After the weight w and the deviation b are obtained, the predicted value of the meteorological data and the predicted value of the control parameters of the heliostat are substituted into the model, and the predicted value of the temperature of the heat transfer medium can be calculated. The specific operation process can be shown in FIG. 4 . Model training is performed based on the historical data set and the constructed initial model to obtain the initial prediction model. Based on the test data set (the test data set is actually historical data, but the historical data is divided into two parts, the large part is used for learning and training, and the small part is used for verification) to test the initial prediction model to determine whether the model is It is desirable, if so, to determine the initial prediction model as the final prediction model. Photothermal conversion prediction based on prediction dataset and final prediction model.

It should be noted here that the present invention adopts the support vector machine SVM algorithm for modeling, and the neural network algorithm can also be considered in practical applications, and the operation process is similar to that of the present invention. To determine the situation, use two methods to model and compare the results, and choose the one that predicts the better results.

Further, the meteorological data may specifically include, but not limited to, any one or more of the following data: irradiance, cloudiness, temperature, humidity, wind speed, and the like.

Further, the control parameter of the heliostat may specifically be the angle of the heliostat and the like.

Step S202 in the embodiment shown in FIG. 2 may specifically include the following steps: predicting the generated power of the solar thermal power generation system based on a thermoelectric numerical model according to the temperature of the heat transfer medium and the flow rate of the heat transfer medium.

Specifically, for the turbine power generation link, the power generation of the CSP system can be predicted according to the temperature of the heat transfer medium and the flow rate of the heat transfer medium. Specifically, a specific calculation formula or a thermoelectric numerical model obtained by machine learning training can be used for prediction. The thermoelectric numerical model may specifically be a support vector machine SVM numerical model.

Further, based on the thermoelectric numerical model, step S202 may specifically include the following steps S303 and S304.

S303 , using the historical data of the temperature of the heat transfer medium and the historical data of the flow of the heat transfer medium as the input, and the historical data of the power generation of the CSP system as the output, train to obtain a thermoelectric numerical model.

Specifically, this step is the training process of the thermoelectric numerical model of the turbine power generation link. The historical data of the temperature of the heat transfer medium and the historical data of the flow of the heat transfer medium are used as the input of the thermoelectric numerical model of the turbine power generation link, and the historical data of the generated power of the CSP system is used as the output of the thermoelectric numerical model of the turbine power generation link , using numerical algorithms such as support vector machine SVM algorithm to train the thermoelectric numerical model of the turbine power generation link. For the specific training process, please refer to the above-mentioned training process of the support vector machine SVM numerical model of the optical-thermal conversion link, but the input and output variables are different, which will not be repeated here.

S304 , using the predicted value of the temperature of the heat transfer medium and the predicted value of the flow rate of the heat transfer medium as input, and based on the thermoelectric numerical model, obtain the predicted value of the output power of the solar thermal power generation system.

Specifically, this step is the prediction process of the thermoelectric numerical model of the turbine power generation link. Taking the predicted value of the temperature of the heat transfer medium (derived from the prediction result of step S302) and the predicted value of the flow of the heat transfer medium (derived from the control system) as the input of the thermoelectric numerical model of the turbine power generation link, based on the trained turbine power generation The thermoelectric numerical model of the link is used to predict, and the predicted value of the generated power of the solar thermal power generation system output by the thermoelectric numerical model of the turbine power generation link is obtained. For the specific prediction process, please refer to the prediction process of the support vector machine SVM numerical model of the above-mentioned light-to-heat conversion link, but the input and output variables are different, which will not be repeated here.

Further, in step S303, when the thermoelectric numerical model is obtained by training, the historical data of the input parameters may also include but are not limited to the historical data of any one or more of the following parameters: the inlet temperature of the heat transfer medium side of the heat exchanger; , the outlet temperature of the heat transfer medium side of the heat exchanger, the inlet temperature of the turbine side of the heat exchanger, the outlet temperature of the turbine side of the heat exchanger, the inlet pressure of the turbine side of the heat exchanger and the inlet flow of the turbine side of the heat exchanger.

Further, in step S304, when the prediction is performed based on the thermoelectric numerical model, the predicted value of the input parameter may also include, but is not limited to, the predicted value of any one or more of the following parameters: Temperature, outlet temperature of heat transfer medium side of heat exchanger, inlet temperature of heat exchanger turbine side, outlet temperature of heat exchanger turbine side, inlet pressure of heat exchanger turbine side and inlet flow rate of heat exchanger turbine side, etc.

Further, the heat transfer medium may specifically be molten salt or the like.

The method for predicting the power of CSP according to the embodiment of the present invention predicts the temperature of the heat transfer medium according to the meteorological data and the control parameters of the heliostat for the light-to-heat conversion link, so as to realize the prediction of the heat energy converted from the light energy by the light-to-heat conversion link. predict. For the turbine power generation link, according to the temperature of the heat transfer medium and the flow rate of the heat transfer medium, the power generation of the CSP system is predicted, and the prediction of the thermal energy converted into electrical energy in the turbine power generation link is realized. To sum up, the method for predicting the CSP power of the embodiment of the present invention can more accurately predict the power generation of the CSP system.

Embodiment 3

FIG. 5 is a schematic structural diagram of an embodiment of the device for predicting CSP power provided by the present invention. The apparatus for predicting CSP power according to the embodiment of the present invention can be used to execute the CSP power prediction method shown in the above-mentioned first or second embodiment. As shown in FIG. 5 , the apparatus for predicting CSP power according to the embodiment of the present invention may specifically include: a first prediction module 51 and a second prediction module 52 .

The first prediction module 51 is configured to predict the temperature of the heat transfer medium according to the meteorological data and the control parameters of the heliostat.

The second prediction module 52 is configured to predict the power generation of the solar thermal power generation system according to the temperature of the heat transfer medium and the flow rate of the heat transfer medium.

Further, the first prediction module 51 can be specifically used for:

According to meteorological data and heliostat control parameters, based on a photothermal numerical model, the temperature of the heat transfer medium is predicted.

Further, the first prediction module 51 can be specifically used for:

Taking the historical data of meteorological data and the historical data of the control parameters of the heliostat as the input, and the historical data of the temperature of the heat transfer medium as the output, the optical-thermal numerical model is obtained by training;

Taking the predicted value of meteorological data and the predicted value of the control parameters of the heliostat as input, and based on the photothermal numerical model, the predicted value of the temperature of the output heat transfer medium is obtained.

Further, the meteorological data may specifically include, but be limited to, any one or more of the following data: irradiance, cloudiness, temperature, humidity, wind speed, and the like.

Further, the control parameter of the heliostat may specifically be the angle of the heliostat and the like.

Further, the second prediction module 52 can be specifically used for:

According to the temperature of the heat transfer medium and the flow rate of the heat transfer medium, based on the thermoelectric numerical model, the power generation of the CSP system is predicted.

Further, the second prediction module 52 can be specifically used for:

Taking the historical data of the temperature of the heat transfer medium and the historical data of the flow of the heat transfer medium as the input, and the historical data of the power generation of the CSP system as the output, the thermoelectric numerical model is obtained by training;

Using the predicted value of the temperature of the heat transfer medium and the predicted value of the flow rate of the heat transfer medium as input, based on the thermoelectric numerical model, the predicted value of the output power of the solar thermal power generation system is obtained.

Further, when the second prediction module 52 is trained to obtain a thermoelectric numerical model, the historical data of the input parameters also include historical data of any one or more of the following parameters: the heat transfer medium side inlet temperature of the heat exchanger, the heat exchange The outlet temperature of the heat transfer medium side of the heat exchanger, the inlet temperature of the turbine side of the heat exchanger, the outlet temperature of the turbine side of the heat exchanger, the inlet pressure of the turbine side of the heat exchanger and the inlet flow rate of the turbine side of the heat exchanger;

When the second prediction module 52 performs prediction based on the thermoelectric numerical model, the predicted value of the input parameter also includes the predicted value of any one or more of the following parameters: Heat medium side outlet temperature, heat exchanger turbine side inlet temperature, heat exchanger turbine side outlet temperature, heat exchanger turbine side inlet pressure and heat exchanger turbine side inlet flow.

Further, the heat transfer medium may specifically be molten salt or the like.

Specifically, for each module in the device for predicting CSP power according to the embodiment of the present invention, the specific process for realizing its function can refer to the CSP power prediction method shown in the above-mentioned Embodiment 1 or 2.

The device for predicting the power of photothermal power generation according to the embodiment of the present invention predicts the temperature of the heat transfer medium according to the meteorological data and the control parameters of the heliostat for the photothermal conversion link, thereby realizing the prediction of the thermal energy converted from the light energy by the photothermal conversion link. predict. For the turbine power generation link, according to the temperature of the heat transfer medium and the flow rate of the heat transfer medium, the power generation of the CSP system is predicted, and the prediction of the thermal energy converted into electrical energy in the turbine power generation link is realized. To sum up, the apparatus for predicting the power of solar thermal power generation according to the embodiment of the present invention can more accurately predict the power generated by the solar thermal power generation system.

Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments may be completed by program instructions related to hardware. The aforementioned program can be stored in a computer-readable storage medium. When the program is executed, the steps including the above method embodiments are executed; and the foregoing storage medium includes: ROM, RAM, magnetic disk or optical disk and other media that can store program codes.

Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, but not to limit them; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: The technical solutions described in the foregoing embodiments can still be modified, or some or all of the technical features thereof can be equivalently replaced; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the technical solutions of the embodiments of the present invention. scope.

Claims (8)

1. A method for predicting photothermal power generation power, comprising:

predicting the temperature of the heat transfer medium based on the photo-thermal numerical model according to meteorological data and heliostat control parameters;

predicting the generated power of the photo-thermal power generation system based on a thermoelectric numerical model according to the temperature of the heat transfer medium and the flow rate of the heat transfer medium,

the historical data of the meteorological data and the historical data of the heliostat control parameters in a two-dimensional array format are used as input, the historical data of the temperature of the heat transfer medium in a one-dimensional array format are used as output, and the photo-thermal numerical model is obtained through training;

obtaining an output predicted value of the temperature of the heat transfer medium based on the photothermal numerical model by taking the predicted value of the meteorological data and the predicted value of the heliostat control parameter as input,

the method comprises the following steps of training to obtain a thermoelectric numerical model by taking historical data of the temperature of the heat transfer medium and historical data of the flow of the heat transfer medium in a two-dimensional array format as inputs and historical data of the power generation power of the photo-thermal power generation system in a one-dimensional array format as outputs;

obtaining a predicted value of the output generated power of the photothermal power generation system based on the thermoelectric numerical model with the predicted value of the temperature of the heat transfer medium and the predicted value of the flow rate of the heat transfer medium as inputs,

wherein the photothermal numerical model and the thermoelectric numerical model are both support vector machine numerical models,

when prediction is performed based on the thermoelectric numerical model, the predicted values of the parameters as input further include the predicted values of any one or more of the following parameters: the heat exchanger heat transfer medium side inlet temperature, the heat exchanger heat transfer medium side outlet temperature, the heat exchanger turbine side inlet temperature, the heat exchanger turbine side outlet temperature, the heat exchanger turbine side inlet pressure, and the heat exchanger turbine side inlet flow.

2. The prediction method of claim 1, wherein the meteorological data comprises any one or more of: irradiance, cloud cover, temperature, humidity, and wind speed.

3. The prediction method according to claim 1, wherein the heliostat control parameter is in particular a heliostat angle.

4. The prediction method of claim 1, wherein the historical data of the parameters as inputs in training the thermoelectric numerical model further comprises historical data of any one or more of the following parameters: the heat exchanger heat transfer medium side inlet temperature, the heat exchanger heat transfer medium side outlet temperature, the heat exchanger turbine side inlet temperature, the heat exchanger turbine side outlet temperature, the heat exchanger turbine side inlet pressure, and the heat exchanger turbine side inlet flow.

5. A photovoltaic power generation power prediction apparatus, comprising:

the first prediction module is used for predicting the temperature of the heat transfer medium based on the photo-thermal numerical model according to meteorological data and heliostat control parameters;

a second prediction module for predicting the generated power of the photo-thermal power generation system based on a thermoelectric numerical model according to the temperature of the heat transfer medium and the flow rate of the heat transfer medium,

wherein the first prediction module is to:

training to obtain the photo-thermal numerical model by taking historical data of the meteorological data and historical data of the heliostat control parameters in a two-dimensional array format as input and taking historical data of the temperature of the heat transfer medium in a one-dimensional array format as output;

obtaining an output predicted value of the temperature of the heat transfer medium based on the photothermal numerical model by taking the predicted value of the meteorological data and the predicted value of the heliostat control parameter as input,

the method comprises the following steps of training to obtain a thermoelectric numerical model by taking historical data of the temperature of the heat transfer medium and historical data of the flow of the heat transfer medium in a two-dimensional array format as inputs and historical data of the power generation power of the photo-thermal power generation system in a one-dimensional array format as outputs;

obtaining a predicted value of the output generated power of the photothermal power generation system based on the thermoelectric numerical model with the predicted value of the temperature of the heat transfer medium and the predicted value of the flow rate of the heat transfer medium as inputs,

wherein the photothermal numerical model and the thermoelectric numerical model are both support vector machine numerical models,

when prediction is performed based on the thermoelectric numerical model, the predicted values of the parameters as input further include the predicted values of any one or more of the following parameters: the heat exchanger heat transfer medium side inlet temperature, the heat exchanger heat transfer medium side outlet temperature, the heat exchanger turbine side inlet temperature, the heat exchanger turbine side outlet temperature, the heat exchanger turbine side inlet pressure, and the heat exchanger turbine side inlet flow.

6. The prediction device of claim 5, wherein the meteorological data comprises any one or more of: irradiance, cloud cover, temperature, humidity, and wind speed.

7. The prediction device according to claim 5, wherein the heliostat control parameter is in particular a heliostat angle.

8. The prediction device of claim 5, wherein when the second prediction module is trained to derive the thermoelectric numerical model, the historical data for the parameters as inputs further comprises historical data for any one or more of the following parameters: the heat exchanger heat transfer medium side inlet temperature, the heat exchanger heat transfer medium side outlet temperature, the heat exchanger turbine side inlet temperature, the heat exchanger turbine side outlet temperature, the heat exchanger turbine side inlet pressure, and the heat exchanger turbine side inlet flow.

Images