Generating capacity prediction method and device of photo-thermal power generation system, equipment and storage medium

Abstract

The invention discloses a generating capacity prediction method, device and equipment of a photo-thermal power generation system and a storage medium, and relates to the technical field of power generation, and the method comprises the steps: collecting historical operation data covering different weather conditions from a photoelectric heating system, the historical operation data comprising radiation intensity, historical generating capacity, environment temperature and wind speed; based on the historical operation data, a generating capacity prediction model is constructed, the generating capacity prediction model comprises a convolutional neural network layer and a long short-term memory network layer, the convolutional neural network layer is used for capturing spatial distribution features, and the long short-term memory network layer is used for capturing time sequence features; acquiring current operation data of the photo-thermal power generation system; and based on the generating capacity prediction model and a preset mechanism, determining predicted generating capacity according to the current operation data. According to the invention, high-precision generating capacity prediction can be realized.

Description

Technical Field

[0001] The present application relates to the field of power generation technology, and in particular to a method, device, equipment and storage medium for predicting power generation of a solar thermal power generation system. Background Art

[0002] In CSP systems, accurately predicting future power generation still faces major challenges. Traditional power generation prediction methods generally have the problem of insufficient prediction accuracy, which will affect the control and operation efficiency of the entire CSP system.

[0003] The above contents are only used to assist in understanding the technical solution of the present application and do not constitute an admission that the above contents are prior art. Summary of the invention

[0004] The main purpose of this application is to provide a method, device, equipment and storage medium for predicting power generation of a solar thermal power generation system, aiming to solve the technical problem of insufficient prediction accuracy commonly found in traditional power generation prediction methods.

[0005] To achieve the above objectives, the present application proposes a method for predicting the power generation of a solar thermal power generation system, the method comprising:

[0006] Collect historical operation data covering different weather conditions from the photovoltaic heating system, wherein the historical operation data includes radiation intensity, historical power generation, ambient temperature and wind speed;

[0007] Based on the historical operation data, a power generation prediction model is constructed, wherein the power generation prediction model includes a convolutional neural network layer and a long short-term memory network layer, the convolutional neural network layer is used to capture spatial distribution characteristics, and the long short-term memory network layer is used to capture time series characteristics;

[0008] Acquiring current operating data of the solar thermal power generation system;

[0009] Based on the power generation prediction model and the preset mechanism, the predicted power generation is determined according to the current operating data.

[0010] In one embodiment, the step of determining the predicted power generation according to the current operation data based on the power generation prediction model and the preset mechanism includes:

[0011] Inputting the current operation data into the power generation prediction model to obtain initial power generation;

[0012] Determining a difference between the initial power generation and the preset power generation;

[0013] When the difference value is greater than a preset threshold, a preset mechanism is activated;

[0014] Under the preset mechanism, matching the corresponding historical values ​​in the historical operation data according to the current operation data;

[0015] The current operation data is corrected based on the historical value, and the corrected current operation data is input into the power generation prediction model to determine the predicted power generation.

[0016] In one embodiment, the step of correcting the current operating data based on the historical value and inputting the corrected current operating data into the power generation prediction model to determine the predicted power generation includes:

[0017] Inputting the corrected current operation data into the power generation prediction model, extracting spatial features of different positions in the solar thermal power generation system through the convolutional neural network layer, and generating a feature map with spatial information according to the spatial features;

[0018] The time dependency and dynamic change characteristics of the historical operation data are extracted from the feature graph through the long short-term memory network layer to output the predicted power generation according to the time dependency and the dynamic change characteristics.

[0019] In one embodiment, the step of constructing a power generation prediction model based on the historical operation data includes:

[0020] Dividing the historical operation data into a training set and a test set;

[0021] Based on the training set, optimizing the model parameters of the initial power generation prediction model to obtain the power generation prediction model;

[0022] Based on the test set, the power generation prediction model is evaluated to obtain an evaluation result, and the power generation prediction model is fine-tuned according to the evaluation result.

[0023] In one embodiment, the step of optimizing the model parameters of the initial power generation prediction model based on the training set to obtain the power generation prediction model includes:

[0024] Determining input data and label data of the training set;

[0025] Inputting the input data into the power generation prediction model to obtain output data;

[0026] Based on the output data and the label data, determining a target loss value according to a mean square error loss function;

[0027] Based on the target loss value, the model parameters of the initial power generation prediction model are optimized by a back propagation algorithm to obtain a power generation prediction model.

[0028] In one embodiment, the step of collecting historical operation data covering different weather conditions from the photovoltaic heating system includes:

[0029] Collecting initial historical operating data covering different weather conditions from the solar thermal power generation system;

[0030] Cleaning the initial historical operation data to remove missing values, abnormal values, and noise values ​​in the initial historical operation data to obtain cleaned data;

[0031] Filling the missing parts in the cleaned data by interpolation or data repair technology to obtain filled data;

[0032] The padded data is scaled to within the processing range of the neural network using a standardization method to obtain historical operation data.

[0033] In one embodiment, the method further comprises:

[0034] monitoring the prediction performance of the power generation prediction model in real time, and when changes are detected in the prediction performance, fine-tuning the power generation prediction model based on regularly updated historical operation data; or,

[0035] When the time interval between the current time and the previous update time is greater than or equal to the model update period, the regularly updated historical operation data is acquired, and the power generation prediction model is fine-tuned based on the regularly updated historical operation data.

[0036] In addition, to achieve the above-mentioned purpose, the present application also proposes a power generation prediction device for a solar thermal power generation system, the power generation prediction device for the solar thermal power generation system comprising:

[0037] A collection module, used to collect historical operation data covering different weather conditions from the photovoltaic heating system, wherein the historical operation data includes radiation intensity, historical power generation, ambient temperature and wind speed;

[0038] A construction module, used to construct a power generation prediction model based on the historical operation data, wherein the power generation prediction model includes a convolutional neural network layer and a long short-term memory network layer, the convolutional neural network layer is used to capture spatial distribution characteristics, and the long short-term memory network layer is used to capture time series characteristics;

[0039] An acquisition module, used to acquire current operation data of the solar thermal power generation system;

[0040] A determination module is used to determine the predicted power generation according to the current operating data based on the power generation prediction model and a preset mechanism.

[0041] In addition, to achieve the above-mentioned purpose, the present application also proposes a power generation prediction device for a solar thermal power generation system, the device comprising: a memory, a processor, and a computer program stored in the memory and executable on the processor, the computer program being configured to implement the steps of the power generation prediction method for the solar thermal power generation system as described above.

[0042] In addition, to achieve the above-mentioned purpose, the present application also proposes a storage medium, which is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the power generation prediction method of the solar thermal power generation system as described above are implemented.

[0043] In addition, to achieve the above-mentioned purpose, the present application also provides a computer program product, which includes a computer program, and when the computer program is executed by a processor, it implements the steps of the power generation prediction method of the solar thermal power generation system as described above.

[0044] One or more technical solutions proposed in this application have at least the following technical effects:

[0045] The power generation prediction method, device, equipment and storage medium of the solar thermal power generation system proposed in the present application collect historical operation data covering different weather conditions from the photovoltaic heating system, wherein the historical operation data includes radiation intensity, historical power generation, ambient temperature and wind speed; based on the historical operation data, a power generation prediction model is constructed, wherein the power generation prediction model includes a convolutional neural network layer and a long short-term memory network layer, the convolutional neural network layer is used to capture spatial distribution characteristics, and the long short-term memory network layer is used to capture time series characteristics; the current operation data of the solar thermal power generation system is obtained; based on the power generation prediction model and the preset mechanism, the predicted power generation is determined according to the current operation data, which solves the technical problem of insufficient prediction accuracy commonly existing in traditional power generation prediction methods. Compared with the prior art, the present application combines the feature extraction capability of the convolutional neural network layer and the time series modeling capability of the long short-term memory network, so that the power generation prediction model can simultaneously capture the spatial characteristics and time series characteristics of the solar thermal power generation system, can reduce the consumption of computing resources while maintaining the prediction accuracy of the model, and ensures that the prediction accuracy can be maintained stably in emergency situations by setting a preset mechanism, thereby achieving high-precision prediction of the solar thermal power generation system. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0047] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0048] Figure 1 A schematic diagram of a flow chart provided for Embodiment 1 of a method for predicting power generation of a solar thermal power generation system of the present application;

[0049] Figure 2 A schematic diagram of a flow chart provided for Embodiment 2 of the method for predicting power generation of a solar thermal power generation system of the present application;

[0050] Figure 3 This is a schematic diagram of the module structure of the power generation prediction device of the solar thermal power generation system of the embodiment of the present application;

[0051] Figure 4 Schematic diagram of the device structure of the hardware operating environment involved in the power generation prediction method of the solar thermal power generation system in the embodiment of the present application.

[0052] The purpose, features and advantages of this application will be further described in conjunction with the embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0053] It should be understood that the specific embodiments described herein are only used to explain the technical solutions of the present application and are not used to limit the present application.

[0054] In order to better understand the technical solution of the present application, a detailed description will be given below in conjunction with the accompanying drawings and specific implementation methods.

[0055] The main solution of the embodiment of the present application is: collecting historical operating data covering different weather conditions from the photovoltaic heating system, wherein the historical operating data includes radiation intensity, historical power generation, ambient temperature and wind speed; constructing a power generation prediction model based on the historical operating data, wherein the power generation prediction model includes a convolutional neural network layer and a long short-term memory network layer, the convolutional neural network layer is used to capture spatial distribution characteristics, and the long short-term memory network layer is used to capture time series characteristics; obtaining the current operating data of the photovoltaic power generation system; based on the power generation prediction model and a preset mechanism, determining the predicted power generation according to the current operating data.

[0056] It can be seen from the above embodiments that the present application collects historical operation data covering different weather conditions from a photovoltaic heating system, wherein the historical operation data includes radiation intensity, historical power generation, ambient temperature and wind speed; based on the historical operation data, a power generation prediction model is constructed, wherein the power generation prediction model includes a convolutional neural network layer and a long short-term memory network layer, the convolutional neural network layer is used to capture spatial distribution characteristics, and the long short-term memory network layer is used to capture time series characteristics; the current operation data of the solar thermal power generation system is obtained; based on the power generation prediction model and the preset mechanism, the predicted power generation is determined according to the current operation data, which solves the technical problem of insufficient prediction accuracy that is common in traditional power generation prediction methods. Compared with the prior art, the present application combines the feature extraction capability of the convolutional neural network layer and the time series modeling capability of the long short-term memory network, so that the power generation prediction model can simultaneously capture the spatial characteristics and time series characteristics of the solar thermal power generation system, and can reduce the consumption of computing resources while maintaining the prediction accuracy of the model, and by setting a preset mechanism to ensure that the stable prediction accuracy can be maintained in emergency situations, thereby achieving high-precision prediction of the solar thermal power generation system.

[0057] It should be noted that the execution subject of this embodiment may be a computing service device with data processing, network communication and program running functions, such as a tablet computer, a personal computer, a mobile phone, etc., or an electronic device capable of realizing the above functions, a power generation prediction device of a solar thermal power generation system, etc. The following takes the power generation prediction device of a solar thermal power generation system as an example to illustrate this embodiment and the following embodiments.

[0058] Based on this, the present application embodiment provides a method for predicting the power generation of a solar thermal power generation system. Figure 1 , Figure 1 This is a flow chart of the first embodiment of the power generation prediction method of the solar thermal power generation system of the present application.

[0059] In this embodiment, the power generation prediction method of the solar thermal power generation system includes steps S10 to S40:

[0060] Step S10, collecting historical operation data covering different weather conditions from the photovoltaic heating system, wherein the historical operation data includes radiation intensity, historical power generation, ambient temperature and wind speed;

[0061] It should be noted that the historical operation data can be obtained through sensors or monitoring equipment; the historical power generation in each set of historical operation data refers to the actual power generation at the previous moment of the set of historical operation data.

[0062] In a feasible implementation, the step of collecting historical operating data covering different weather conditions from the photovoltaic heating system includes: collecting initial historical operating data covering different weather conditions from the photovoltaic heating system; cleaning the initial historical operating data, removing missing values, abnormal values ​​and noise values ​​in the initial historical operating data, and obtaining cleaned data; filling the missing parts in the cleaned data by interpolation or data repair technology to obtain filled data; and using a standardized method to scale the filled data to within the processing range of the neural network to obtain historical operating data.

[0063] It should be noted that the collected raw data (i.e. the initial historical running data) is cleaned to remove missing values, outliers and noise. The gaps in the data are filled by interpolation or other data repair methods. The data is scaled to a range suitable for processing by the neural network model using a standardization method. This step ensures that the model will not have convergence problems due to numerical differences during training.

[0064] Step S20, constructing a power generation prediction model based on the historical operation data, wherein the power generation prediction model includes a convolutional neural network layer and a long short-term memory network layer, the convolutional neural network layer is used to capture spatial distribution characteristics, and the long short-term memory network layer is used to capture time series characteristics;

[0065] It should be noted that when designing the CNN-LSTM model (i.e., the power generation prediction model), the CNN layer (i.e., the convolutional neural network layer) is first used to extract spatial features. The CNN layer captures the spatial distribution characteristics of input data such as temperature and radiation intensity through convolution operations to form a feature map with spatial information. The feature map is input into the LSTM layer (i.e., the long short-term memory network layer), and the memory and sequence processing capabilities of LSTM are used to model the changing trends of these spatial features over time, thereby capturing the time dependency and dynamic change characteristics in the historical data.

[0066] In a feasible implementation manner, the step of constructing a power generation prediction model based on the historical operation data includes: dividing the historical operation data into a training set and a test set; based on the training set, optimizing the model parameters of the initial power generation prediction model to obtain a power generation prediction model; based on the test set, evaluating the power generation prediction model to obtain an evaluation result, and fine-tuning the power generation prediction model according to the evaluation result.

[0067] It should be noted that adjusting the hyperparameters of the power generation prediction model specifically includes adjusting the convolution kernel size of the CNN layer, the number of hidden units of the LSTM layer, the learning rate, and the batch size; and finding the best hyperparameter combination through a random search method to further improve the prediction performance of the model.

[0068] In a feasible implementation manner, the step of optimizing the model parameters of the initial power generation prediction model based on the training set to obtain the power generation prediction model includes: determining the input data and label data of the training set; inputting the input data into the power generation prediction model to obtain output data; determining a target loss value based on the output data and the label data according to a mean square error loss function; and optimizing the model parameters of the initial power generation prediction model through a back propagation algorithm based on the target loss value to obtain the power generation prediction model.

[0069] In the specific implementation, the historical operation data can be divided into a training set and a test set to train the CNN-LSTM model (i.e., the power generation prediction model). The loss function of the model can be set to the mean square error (MSE) loss function, and the model parameters can be optimized through the back propagation algorithm. During the training process, the performance of the model is monitored in real time through the validation set, and the early stopping strategy is used to prevent the model from overfitting. After the model training is completed, the generalization ability and prediction accuracy of the model are evaluated using the test set.

[0070] Step S30, obtaining current operation data of the solar thermal power generation system;

[0071] It should be noted that the current operating data includes radiation intensity, historical power generation, ambient temperature and wind speed. The historical power generation in the current operating data refers to the actual power generation at the previous moment before the current moment.

[0072] Step S40, based on the power generation prediction model and the preset mechanism, determine the predicted power generation according to the current operating data.

[0073] It should be noted that the preset mechanism can be set in advance. The preset mechanism is a mechanism that is activated when the difference between the predicted value and the preset value is monitored to be too large during the prediction process of the power generation prediction model. Under this preset mechanism, the historical power generation in the current operating data needs to be replaced with the historical power generation in the historical operating data that matches the current operating data. The historical power generation in the current operating data can also be replaced with the actual power generation measured in real time by the sensor at the current moment, and then the corrected current operating data is input into the power generation prediction model to obtain the final predicted power generation. This method can effectively suppress error accumulation, thereby significantly improving the preset stability and accuracy.

[0074] In a feasible implementation, the method further includes: monitoring the prediction performance of the power generation prediction model in real time, and when the prediction performance is monitored to change, fine-tuning the power generation prediction model based on regularly updated historical operation data; or, when the time interval between the current time and the previous update time is greater than or equal to the model update period, obtaining regularly updated historical operation data, and fine-tuning the power generation prediction model based on the regularly updated historical operation data.

[0075] It should be noted that the prediction performance of the power generation prediction model can be monitored in real time. When a significant change is detected in the system operating environment or input data (for example, when the prediction accuracy of the power generation prediction model is low, the model needs to be retrained or the model parameters of the model need to be fine-tuned), the power generation prediction model retraining or fine-tuning process is triggered to ensure that the model continues to maintain high accuracy. The model training data can also be updated regularly, and the model can be retrained based on the new data to adapt to possible long-term trend changes, such as seasonal changes or equipment aging.

[0076] This embodiment collects historical operation data covering different weather conditions from the photovoltaic heating system, wherein the historical operation data includes radiation intensity, historical power generation, ambient temperature and wind speed; based on the historical operation data, constructs a power generation prediction model, wherein the power generation prediction model includes a convolutional neural network layer and a long short-term memory network layer, the convolutional neural network layer is used to capture spatial distribution characteristics, and the long short-term memory network layer is used to capture time series characteristics; obtains the current operation data of the photovoltaic power generation system; based on the power generation prediction model and the preset mechanism, determines the predicted power generation according to the current operation data, solves the technical problem of insufficient prediction accuracy commonly existing in traditional power generation prediction methods, compared with the prior art, the present application combines the feature extraction capability of the convolutional neural network layer and the time series modeling capability of the long short-term memory network, so that the power generation prediction model can simultaneously capture the spatial characteristics and time series characteristics of the photovoltaic power generation system, can reduce the consumption of computing resources while maintaining the prediction accuracy of the model, and ensures that the stable prediction accuracy can be maintained in emergency situations by setting a preset mechanism, thereby achieving high-precision prediction of the photovoltaic power generation system.

[0077] Based on the first embodiment of the present application, in the second embodiment of the present application, the same or similar contents as those in the above-mentioned embodiment 1 can be referred to the above introduction, and will not be repeated in the following. Figure 2 , step S40 also includes steps S401 to S405:

[0078] Step S401, inputting the current operation data into the power generation prediction model to obtain initial power generation;

[0079] It should be noted that the current operating data refers to the radiation intensity, historical power generation, ambient temperature and wind speed obtained at the current moment. The historical power generation in the current operating data refers to the actual power generation at the previous moment corresponding to the current moment. The power generation prediction model adopts multi-step prediction to realize power generation prediction, which means using historical operating data to predict the power generation at multiple time points (or steps) in the future. The multi-step prediction method is mainly divided into direct multi-step prediction method, iterative multi-step prediction method, direct-iterative combined multi-step prediction method and multi-output multi-step prediction method.

[0080] Step S402, determining the difference between the initial power generation and the preset power generation;

[0081] It should be noted that the preset power generation can be set in advance. When the difference between the initial power generation and the preset power generation is greater than the preset threshold, it means that the prediction of the power generation prediction model at this time is not accurate enough. At this time, it is necessary to start the preset mechanism (that is, update the historical power generation in the current operating data to the historical power generation in the historical operating data).

[0082] Step S403, when the difference value is greater than a preset threshold, a preset mechanism is activated;

[0083] It should be noted that the preset threshold can be set in advance according to actual conditions; the preset mechanism is a mechanism that is activated when the difference between the predicted value and the preset value is monitored to be too large during the prediction process of the power generation prediction model. Under this preset mechanism, the historical power generation in the current operating data needs to be replaced with the historical power generation in the historical operating data that matches the current operating data, and the historical power generation in the current operating data can also be replaced with the actual power generation measured in real time by the sensor at the current moment, and then the corrected current operating data is input into the power generation prediction model to obtain the final predicted power generation. This method can effectively suppress error accumulation, thereby significantly improving the preset stability and accuracy.

[0084] Step S404, matching the corresponding historical values ​​in the historical operation data according to the current operation data under the preset mechanism;

[0085] It should be noted that historical operating data that matches the current operating data can be determined. For example, when the radiation intensity, ambient temperature and wind speed in the current operating data and the historical operating data are almost completely consistent, it can be determined that the current operating data matches the historical operating data; the historical value refers to the historical power generation in the historical operating data when the current operating data matches the historical operating data.

[0086] Step S405, correcting the current operation data based on the historical value, and inputting the corrected current operation data into the power generation prediction model to determine the predicted power generation.

[0087] It should be noted that after the historical power generation in the current operation data is updated to the historical power generation in the historical operation data, the updated current operation data can be input into the power generation prediction model to output the predicted power generation.

[0088] In a feasible implementation manner, the current operating data is corrected based on the historical value, and the corrected current operating data is input into the power generation prediction model. The step of determining the predicted power generation includes: inputting the corrected current operating data into the power generation prediction model, extracting the spatial features of different positions in the solar thermal power generation system through the convolutional neural network layer, and generating a feature map with spatial information based on the spatial features; extracting the time dependency and dynamic change characteristics of the historical operating data from the feature map through the long short-term memory network layer, so as to output the predicted power generation based on the time dependency and the dynamic change characteristics.

[0089] It should be noted that the power generation prediction model can be designed as a CNN-LSTM model. First, the CNN layer is used to extract spatial features. The CNN layer captures the spatial distribution characteristics of input data such as temperature and radiation intensity through convolution operations to form a feature map with spatial information. The feature map is input to the LSTM layer, and the memory and sequence processing capabilities of LSTM are used to model the change trend of these spatial features over time, thereby capturing the time dependency and dynamic change characteristics in historical data.

[0090] It is understandable that the CNN-LSTM composite model combines information from the spatial and temporal dimensions, extracting spatial features through the CNN network and capturing the dynamic changes of the time series through the LSTM time series network. This dual feature extraction and modeling method enables the model to more accurately capture the complex relationship between variables such as input and output in the CSP system, thereby improving the accuracy of multi-step predictions, helping the system to more accurately schedule and optimize the CSP process, thereby maximizing power generation efficiency, reducing energy waste, and improving the overall system operation effect.

[0091] This embodiment obtains the initial power generation by inputting the current operation data into the power generation prediction model; determines the difference between the initial power generation and the preset power generation; when the difference is greater than a preset threshold, starts a preset mechanism; under the preset mechanism, matches the corresponding historical value in the historical operation data according to the current operation data; corrects the current operation data based on the historical value, and inputs the corrected current operation data into the power generation prediction model to determine the predicted power generation. Through the above method, the present application can monitor the difference between the predicted initial power generation and the preset power generation in real time during the prediction process of the power generation prediction model. When the prediction error exceeds the preset threshold, the preset mechanism is automatically started, matches the current state according to the historical data, and replaces the real value with the historical value. This mechanism effectively suppresses error accumulation, especially in multi-step prediction tasks, and significantly improves the stability and accuracy of the prediction.

[0092] It should be noted that the above examples are only used to understand the present application and do not constitute a limitation on the power generation prediction method of the solar thermal power generation system of the present application. More simple transformations based on this technical concept are all within the protection scope of the present application.

[0093] This application also provides a power generation prediction device for a solar thermal power generation system. Figure 3 , the power generation prediction device of the solar thermal power generation system comprises:

[0094] The collecting module 10 is used to collect historical operation data covering different weather conditions from the photovoltaic heating system, wherein the historical operation data includes radiation intensity, historical power generation, ambient temperature and wind speed;

[0095] A construction module 20 is used to construct a power generation prediction model based on the historical operation data, wherein the power generation prediction model includes a convolutional neural network layer and a long short-term memory network layer, the convolutional neural network layer is used to capture spatial distribution characteristics, and the long short-term memory network layer is used to capture time series characteristics;

[0096] An acquisition module 30 is used to acquire current operation data of the solar thermal power generation system;

[0097] The determination module 40 is used to determine the predicted power generation according to the current operation data based on the power generation prediction model and the preset mechanism.

[0098] The power generation prediction device of the solar thermal power generation system provided in the present application adopts the power generation prediction method of the solar thermal power generation system in the above embodiment, which can solve the technical problem of insufficient prediction accuracy that is common in traditional power generation prediction methods. Compared with the prior art, the beneficial effects of the power generation prediction device of the solar thermal power generation system provided in the present application are the same as the beneficial effects of the power generation prediction method of the solar thermal power generation system provided in the above embodiment, and the other technical features of the power generation prediction device of the solar thermal power generation system are the same as the features disclosed in the above embodiment method, which will not be repeated here.

[0099] The present application provides a power generation prediction device for a solar thermal power generation system, the power generation prediction device for the solar thermal power generation system comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the power generation prediction method for the solar thermal power generation system in the above-mentioned embodiment one.

[0100] Reference below Figure 4 , which shows a schematic diagram of the structure of a power generation prediction device for a solar thermal power generation system suitable for implementing the embodiment of the present application. The power generation prediction device for a solar thermal power generation system in the embodiment of the present application may include but is not limited to mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Portable Application Descriptions), PMPs (Portable Media Players), vehicle-mounted terminals (such as vehicle-mounted navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 4 The power generation prediction device of the solar thermal power generation system shown is only an example and should not bring any limitation to the functions and scope of use of the embodiments of the present application.

[0101] like Figure 4As shown, the power generation prediction device of the solar thermal power generation system may include a processing device 1001 (such as a central processing unit, a graphics processing unit, etc.), which can perform various appropriate actions and processes according to the program stored in the read-only memory (ROM: Read Only Memory) 1002 or the program loaded from the storage device 1003 to the random access memory (RAM: Random Access Memory) 1004. Various programs and data required for the operation of the power generation prediction device of the solar thermal power generation system are also stored in RAM1004. The processing device 1001, ROM1002 and RAM1004 are connected to each other through a bus 1005. The input / output (I / O) interface 1006 is also connected to the bus. Typically, the following systems can be connected to the I / O interface 1006: input devices 1007 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; output devices 1008 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; storage devices 1003 including, for example, a magnetic tape, a hard disk, etc.; and communication devices 1009. The communication device 1009 can allow the power generation prediction device of the solar thermal power generation system to communicate with other devices wirelessly or by wire to exchange data. Although the figure shows a power generation prediction device of a solar thermal power generation system with various systems, it should be understood that it is not required to implement or have all the systems shown. More or fewer systems may be implemented or have alternatively.

[0102] In particular, according to the embodiments disclosed in the present application, the process described above with reference to the flowchart can be implemented as a computer software program. For example, the embodiments disclosed in the present application include a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program includes a program code for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from a network through a communication device, or installed from a storage device 1003, or installed from a ROM 1002. When the computer program is executed by the processing device 1001, the above-mentioned functions defined in the method of the embodiment disclosed in the present application are executed.

[0103] The power generation prediction device of the solar thermal power generation system provided in the present application adopts the power generation prediction method of the solar thermal power generation system in the above embodiment, which can solve the technical problem of insufficient prediction accuracy commonly existing in the traditional power generation prediction method. Compared with the prior art, the beneficial effects of the power generation prediction device of the solar thermal power generation system provided in the present application are the same as the beneficial effects of the power generation prediction method of the solar thermal power generation system provided in the above embodiment, and the other technical features of the power generation prediction device of the solar thermal power generation system are the same as the features disclosed in the method of the previous embodiment, which will not be repeated here.

[0104] It should be understood that the various parts disclosed in this application can be implemented by hardware, software, firmware or a combination thereof. In the description of the above embodiments, specific features, structures, materials or characteristics can be combined in any one or more embodiments or examples in a suitable manner.

[0105] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any person skilled in the art who is familiar with the present technical field can easily think of changes or substitutions within the technical scope disclosed in the present application, which should be included in the protection scope of the present application. Therefore, the protection scope of the present application should be based on the protection scope of the claims.

[0106] The present application provides a computer-readable storage medium having computer-readable program instructions (ie, computer programs) stored thereon, and the computer-readable program instructions are used to execute the power generation prediction method of the solar thermal power generation system in the above-mentioned embodiment.

[0107] The computer-readable storage medium provided in the present application may be, for example, a USB flash drive, but is not limited to electrical, magnetic, optical, electromagnetic, infrared, or semiconductor systems, systems or devices, or any combination of the above. More specific examples of computer-readable storage media may include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this embodiment, the computer-readable storage medium may be any tangible medium containing or storing a program that can be used by or in combination with an instruction execution system, system or device. The program code contained on the computer-readable storage medium may be transmitted using any appropriate medium, including but not limited to: wires, optical cables, RF (Radio Frequency), etc., or any suitable combination of the above.

[0108] The computer-readable storage medium may be included in the power generation prediction device of the solar thermal power generation system; or may exist independently without being assembled into the power generation prediction device of the solar thermal power generation system.

[0109] The computer-readable storage medium carries one or more programs. When the one or more programs are executed by the power generation prediction device of the solar thermal power generation system, the power generation prediction device of the solar thermal power generation system: collects historical operation data covering different weather conditions from the photovoltaic heating system, wherein the historical operation data includes radiation intensity, historical power generation, ambient temperature and wind speed; constructs a power generation prediction model based on the historical operation data, wherein the power generation prediction model includes a convolutional neural network layer and a long short-term memory network layer, the convolutional neural network layer is used to capture spatial distribution characteristics, and the long short-term memory network layer is used to capture time series characteristics; obtains the current operation data of the solar thermal power generation system; and determines the predicted power generation according to the current operation data based on the power generation prediction model and a preset mechanism.

[0110] Computer program code for performing the operations of the present application may be written in one or more programming languages ​​or a combination thereof, including object-oriented programming languages ​​such as Java, Smalltalk, C++, and conventional procedural programming languages ​​such as "C" or similar programming languages. The program code may be executed entirely on the user's computer, partially on the user's computer, as a separate software package, partially on the user's computer and partially on a remote computer, or entirely on a remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., via the Internet using an Internet service provider).

[0111] The flow chart and block diagram in the accompanying drawings illustrate the possible architecture, function and operation of the system, method and computer program product according to various embodiments of the present application. In this regard, each square box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, the program segment or a part of the code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the square box can also occur in a sequence different from that marked in the accompanying drawings. For example, two square boxes represented in succession can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved. It should also be noted that each square box in the block diagram and / or flow chart, and the combination of the square boxes in the block diagram and / or flow chart can be implemented with a dedicated hardware-based system that performs a specified function or operation, or can be implemented with a combination of dedicated hardware and computer instructions.

[0112] The modules involved in the embodiments described in this application may be implemented by software or hardware, wherein the name of the module does not constitute a limitation on the unit itself in some cases.

[0113] The readable storage medium provided in this application is a computer-readable storage medium, which stores computer-readable program instructions (i.e., computer programs) for executing the above-mentioned method for predicting the power generation of the solar thermal power generation system, and can solve the technical problem of insufficient prediction accuracy that is common in traditional power generation prediction methods. Compared with the prior art, the beneficial effects of the computer-readable storage medium provided in this application are the same as the beneficial effects of the method for predicting the power generation of the solar thermal power generation system provided in the above-mentioned embodiment, and will not be repeated here.

[0114] The present application also provides a computer program product, including a computer program, which, when executed by a processor, implements the steps of the above-mentioned method for predicting power generation of a solar thermal power generation system.

[0115] The computer program product provided in this application can solve the technical problem of insufficient prediction accuracy that is common in traditional power generation prediction methods. Compared with the prior art, the beneficial effects of the computer program product provided in this application are the same as the beneficial effects of the power generation prediction method of the solar thermal power generation system provided in the above embodiment, which will not be repeated here.

[0116] The above descriptions are only some embodiments of the present application, and are not intended to limit the patent scope of the present application. All equivalent structural changes made using the contents of the present application specification and drawings under the technical concept of the present application, or direct / indirect applications in other related technical fields are included in the patent protection scope of the present application.

Claims

1. A method for predicting power generation of a solar thermal power generation system, characterized in that: The method comprises: Collect historical operation data covering different weather conditions from the photovoltaic heating system, wherein the historical operation data includes radiation intensity, historical power generation, ambient temperature and wind speed; Based on the historical operation data, a power generation prediction model is constructed, wherein the power generation prediction model includes a convolutional neural network layer and a long short-term memory network layer, the convolutional neural network layer is used to capture spatial distribution characteristics, and the long short-term memory network layer is used to capture time series characteristics; Acquiring current operating data of the solar thermal power generation system; Based on the power generation prediction model and the preset mechanism, the predicted power generation is determined according to the current operating data.

2. The method according to claim 1, characterized in that The step of determining the predicted power generation according to the current operation data based on the power generation prediction model and the preset mechanism comprises: Inputting the current operation data into the power generation prediction model to obtain initial power generation; Determining a difference between the initial power generation and the preset power generation; When the difference value is greater than a preset threshold, a preset mechanism is activated; Under the preset mechanism, matching the corresponding historical values ​​in the historical operation data according to the current operation data; The current operation data is corrected based on the historical value, and the corrected current operation data is input into the power generation prediction model to determine the predicted power generation.

3. The method according to claim 2, characterized in that The step of correcting the current operation data based on the historical value and inputting the corrected current operation data into the power generation prediction model to determine the predicted power generation includes: Inputting the corrected current operation data into the power generation prediction model, extracting spatial features of different positions in the solar thermal power generation system through the convolutional neural network layer, and generating a feature map with spatial information according to the spatial features; The time dependency and dynamic change characteristics of the historical operation data are extracted from the feature graph through the long short-term memory network layer to output the predicted power generation according to the time dependency and the dynamic change characteristics.

4. The method according to claim 1, characterized in that The step of constructing a power generation prediction model based on the historical operation data comprises: Dividing the historical operation data into a training set and a test set; Based on the training set, optimizing the model parameters of the initial power generation prediction model to obtain the power generation prediction model; Based on the test set, the power generation prediction model is evaluated to obtain an evaluation result, and the power generation prediction model is fine-tuned according to the evaluation result.

5. The method according to claim 4, characterized in that The step of optimizing the model parameters of the initial power generation prediction model based on the training set to obtain the power generation prediction model comprises: Determining input data and label data of the training set; Inputting the input data into the power generation prediction model to obtain output data; Based on the output data and the label data, determining a target loss value according to a mean square error loss function; Based on the target loss value, the model parameters of the initial power generation prediction model are optimized by a back propagation algorithm to obtain a power generation prediction model.

6. The method according to claim 1, characterized in that The step of collecting historical operation data covering different weather conditions from the photovoltaic heating system comprises: Collecting initial historical operating data covering different weather conditions from the solar thermal power generation system; Cleaning the initial historical operation data to remove missing values, abnormal values, and noise values ​​in the initial historical operation data to obtain cleaned data; Filling the missing parts in the cleaned data by interpolation or data repair technology to obtain filled data; The padded data is scaled to within the processing range of the neural network using a standardization method to obtain historical operation data.

7. The method according to claim 1, characterized in that The method further comprises: monitoring the prediction performance of the power generation prediction model in real time, and when changes are detected in the prediction performance, fine-tuning the power generation prediction model based on regularly updated historical operation data; or, When the time interval between the current time and the previous update time is greater than or equal to the model update period, the regularly updated historical operation data is acquired, and the power generation prediction model is fine-tuned based on the regularly updated historical operation data.

8. A power generation prediction device for a solar thermal power generation system, characterized in that: The device comprises: A collection module, used to collect historical operation data covering different weather conditions from the photovoltaic heating system, wherein the historical operation data includes radiation intensity, historical power generation, ambient temperature and wind speed; A construction module, used to construct a power generation prediction model based on the historical operation data, wherein the power generation prediction model includes a convolutional neural network layer and a long short-term memory network layer, the convolutional neural network layer is used to capture spatial distribution characteristics, and the long short-term memory network layer is used to capture time series characteristics; An acquisition module, used to acquire current operation data of the solar thermal power generation system; A determination module is used to determine the predicted power generation according to the current operating data based on the power generation prediction model and a preset mechanism.

9. A power generation prediction device for a solar thermal power generation system, characterized in that: The device comprises: a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the computer program is configured to implement the steps of the method for predicting power generation of a solar thermal power generation system according to any one of claims 1 to 7.

10. A storage medium, characterized in that: The storage medium is a computer-readable storage medium, and a computer program is stored on the storage medium. When the computer program is executed by a processor, the steps of the method for predicting power generation of a solar thermal power generation system according to any one of claims 1 to 7 are implemented.

Images