CN114254556A - Photovoltaic power generation power prediction method and device, electronic equipment and storage medium - Google Patents
Photovoltaic power generation power prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN114254556A CN114254556A CN202111374757.3A CN202111374757A CN114254556A CN 114254556 A CN114254556 A CN 114254556A CN 202111374757 A CN202111374757 A CN 202111374757A CN 114254556 A CN114254556 A CN 114254556A
- Authority
- CN
- China
- Prior art keywords
- power generation
- photovoltaic power
- layer
- historical
- generation power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2119/00—Details relating to the type or aim of the analysis or the optimisation
- G06F2119/06—Power analysis or power optimisation
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Theoretical Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Software Systems (AREA)
- Artificial Intelligence (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Supply And Distribution Of Alternating Current (AREA)
Abstract
The application provides a method and a device for predicting photovoltaic power generation power, electronic equipment and a storage medium, wherein the method comprises the following steps: the method comprises the steps of obtaining a prediction day, corresponding working conditions and weather data, obtaining historical sampling days with the working conditions and the weather data matched with the prediction day, and historical photovoltaic power generation power of the historical sampling days at each sampling moment, inputting the historical photovoltaic power generation power of the historical sampling days at each sampling moment into a photovoltaic power generation power prediction model, and obtaining a photovoltaic power generation power prediction value of the prediction day at each sampling moment. Therefore, in the process of predicting the photovoltaic power generation power, the photovoltaic power generation power of the historical sampling day matched with the prediction day is combined with the working condition and weather data to predict the photovoltaic power generation power of the prediction day, and the photovoltaic power generation power prediction value corresponding to the prediction day is accurately predicted through the photovoltaic power generation power prediction model.
Description
Technical Field
The present application relates to the field of photovoltaic power generation technologies, and in particular, to a method and an apparatus for predicting photovoltaic power generation power, an electronic device, and a storage medium.
Background
The prediction of the photovoltaic power generation power has great significance for site selection and grid connection of a photovoltaic power plant. Therefore, how to accurately predict the photovoltaic power generation power is a technical problem which needs to be solved urgently at present.
Disclosure of Invention
The application provides a method and a device for predicting photovoltaic power generation power, electronic equipment and a storage medium.
The embodiment of the first aspect of the application provides a method for predicting photovoltaic power generation power, and the method comprises the steps of obtaining a prediction day and corresponding working condition and weather data; acquiring historical sampling days matched with the working condition and weather data and the prediction days; acquiring historical photovoltaic power generation power of the historical sampling days at each sampling moment; and inputting the historical photovoltaic power generation power of the historical sampling days at each sampling moment into a photovoltaic power generation power prediction model to obtain the photovoltaic power generation power prediction value of the prediction days at each sampling moment.
In an embodiment of the application, the photovoltaic power generation power prediction model includes an input layer, a convolutional neural network CNN layer, a long-short term memory artificial neural network LSTM layer, an attention layer, and an output layer, and the inputting the historical photovoltaic power generation power at each sampling time on the historical sampling day into the photovoltaic power generation power prediction model to obtain the photovoltaic power generation power predicted value at each sampling time on the prediction day includes: inputting the historical photovoltaic power generation power of the historical sampling days at each sampling moment into the input layer, and obtaining input vectors corresponding to the historical photovoltaic power generation power through the input layer; inputting the input vector into the CNN layer, and performing feature extraction on the input vector to screen out a target feature vector; acquiring the target characteristic vectors, and inputting the target characteristic vectors into the LSTM layer to obtain first output vectors corresponding to the target characteristic vectors respectively; inputting first output vectors corresponding to the target feature vectors into the attention layer, and screening the first output vectors according to attention weight parameter values of the first output vectors in the attention layer to obtain second output vectors; and inputting the second output vector into the output layer to obtain a photovoltaic power generation power predicted value of the predicted day at each sampling moment.
In one embodiment of the present application, the CNN layer includes a convolutional layer and a discard dropout layer, the inputting the input vector into the CNN layer, and performing feature extraction on the input vector to filter out a target feature vector, including: inputting the input vector into the convolutional layer to obtain a plurality of characteristic vectors of the input vector extracted by the convolutional layer; inputting a plurality of feature vectors of the input vector into the dropout layer to screen out a target feature vector from the plurality of features.
In an embodiment of the present application, after inputting the second output vector to the output layer to obtain a predicted photovoltaic power generation power value of the prediction day at each sampling time, the method further includes: and carrying out reverse normalization processing on the photovoltaic power generation power predicted value of the prediction day at each sampling moment.
The application provides a photovoltaic power generation power prediction method, which includes the steps of obtaining a prediction day, corresponding working conditions and weather data, historical sampling days with the working conditions and the weather data matched with the prediction day, and historical photovoltaic power generation power of the historical sampling days at each sampling moment, inputting the historical photovoltaic power generation power of the historical sampling days at each sampling moment into a photovoltaic power generation power prediction model, and accordingly obtaining a photovoltaic power generation power prediction value of the prediction day at each sampling moment. Therefore, in the process of predicting the photovoltaic power generation power, the photovoltaic power generation power of the historical sampling day matched with the prediction day is combined with the working condition and weather data to predict the photovoltaic power generation power of the prediction day, and the photovoltaic power generation power prediction value corresponding to the prediction day is accurately predicted through the photovoltaic power generation power prediction model.
The embodiment of the second aspect of the present application provides a device for predicting photovoltaic power generation power, where the device includes: the first acquisition module is used for acquiring the predicted day and corresponding working condition and weather data; the second acquisition module is used for acquiring historical sampling days matched with the working condition and weather data and the prediction days; the third acquisition module is used for acquiring historical photovoltaic power generation power of the historical sampling days at each sampling moment; and the generation module is used for inputting the historical photovoltaic power generation power of the historical sampling days at each sampling moment into a photovoltaic power generation power prediction model so as to obtain the photovoltaic power generation power prediction value of the prediction days at each sampling moment.
In an embodiment of the application, the photovoltaic power generation power prediction model includes an input layer, a convolutional neural network CNN layer, a long-short term memory artificial neural network LSTM layer, an attention layer, and an output layer, and the generation module includes: the input unit is used for inputting the historical photovoltaic power generation power of the historical sampling day at each sampling moment into the input layer and obtaining input vectors corresponding to the historical photovoltaic power generation power through the input layer; the extraction unit is used for inputting the input vector into the CNN layer and extracting the characteristics of the input vector to screen out a target characteristic vector; the first generating unit is used for acquiring the target characteristic vectors and inputting the target characteristic vectors into the LSTM layer to obtain first output vectors corresponding to the target characteristic vectors; a second generating unit, configured to input first output vectors corresponding to the target feature vectors into the attention layer, and filter the first output vectors according to attention weight parameter values of the first output vectors in the attention layer to obtain second output vectors; and the output unit is used for inputting the second output vector into the output layer so as to obtain the photovoltaic power generation power predicted value of the predicted day at each sampling moment.
In an embodiment of the present application, the CNN layer includes a convolution layer and a discard dropout layer, and the extracting unit is specifically configured to: inputting the input vector into the convolutional layer to obtain a plurality of characteristic vectors of the input vector extracted by the convolutional layer; inputting a plurality of feature vectors of the input vector into the dropout layer to screen out a target feature vector from the plurality of features.
In one embodiment of the present application, the generating module further includes: and the processing unit is used for carrying out inverse normalization processing on the photovoltaic power generation power predicted value of the predicted day at each sampling moment.
The application provides a photovoltaic power generation power prediction device, which is used for obtaining a prediction day, corresponding working conditions and weather data, historical sampling days matched with the prediction day according to the working conditions and the weather data, and historical photovoltaic power generation power of the historical sampling days at each sampling moment, inputting the historical photovoltaic power generation power of the historical sampling days at each sampling moment into a photovoltaic power generation power prediction model, and obtaining a photovoltaic power generation power prediction value of the prediction day at each sampling moment. Therefore, in the process of predicting the photovoltaic power generation power, the photovoltaic power generation power of the historical sampling day matched with the prediction day is combined with the working condition and weather data to predict the photovoltaic power generation power of the prediction day, and the photovoltaic power generation power prediction value corresponding to the prediction day is accurately predicted through the photovoltaic power generation power prediction model.
An embodiment of a third aspect of the present application provides an electronic device, including: the device comprises a memory, a processor and a computer program stored on the memory and capable of running on the processor, wherein the program is executed by the processor to realize the photovoltaic power generation power prediction method in the embodiment of the application.
A fourth aspect of the present application provides a computer-readable storage medium, on which a computer program is stored, where the program is executed by a processor, and the method for predicting photovoltaic power generation power in the embodiment of the present application is provided.
Other effects of the above-described alternative will be described below with reference to specific embodiments.
Drawings
Fig. 1 is a schematic flowchart of a method for predicting photovoltaic power generation provided in an embodiment of the present application;
FIG. 2 is a schematic structural diagram of a photovoltaic power generation power prediction model provided in an embodiment of the present application;
FIG. 3 is a schematic flow chart of another photovoltaic power generation power prediction method provided by the embodiment of the present application;
fig. 4 is a schematic structural diagram of a dropout layer according to an embodiment of the present disclosure;
FIG. 5 is a structural diagram of a photovoltaic power generation prediction device provided by an embodiment of the present application;
FIG. 6 is a structural illustration of another photovoltaic power generation power prediction device provided by an embodiment of the present application;
FIG. 7 is a block diagram of an electronic device of one embodiment of the present application.
Detailed Description
Reference will now be made in detail to the embodiments of the present application, examples of which are illustrated in the accompanying drawings, wherein like or similar reference numerals refer to the same or similar elements or elements having the same or similar function throughout. The embodiments described below with reference to the drawings are exemplary and intended to be used for explaining the present application and should not be construed as limiting the present application.
The following describes a prediction method, a prediction device, and an electronic device of photovoltaic power generation power according to an embodiment of the present application with reference to the drawings.
Fig. 1 is a schematic flowchart of a method for predicting photovoltaic power generation provided in an embodiment of the present application. It should be noted that an execution subject of the method for predicting photovoltaic power generation provided in this embodiment is a device for predicting photovoltaic power generation, the device for predicting photovoltaic power generation may be implemented in a software and/or hardware manner, the device for predicting photovoltaic power generation in this embodiment may be configured in an electronic device, the electronic device in this embodiment may include a server, and the embodiment does not specifically limit the electronic device.
Fig. 1 is a schematic flowchart of a method for predicting photovoltaic power generation provided in an embodiment of the present application.
As shown in fig. 1, the method for predicting photovoltaic power generation power may include:
In some embodiments, the condition and weather data corresponding to the predicted day may be, but is not limited to, data provided by a relatively reliable mechanism such as a weather station.
And 102, acquiring historical sampling days matched with the predicted days according to the working conditions and the weather data.
In some embodiments, the operating condition and weather data corresponding to the predicted day are combined, and historical sampling days matched with the operating condition and weather data and the predicted day are screened out from the historical data in a time sequence.
And 103, acquiring historical photovoltaic power generation power of each sampling moment on a historical sampling day.
In some embodiments, the historical photovoltaic power generation power of the historical sampling days at each sampling moment is acquired, and since the illumination time is concentrated in the daytime, 10 integral time points in the period of 08:00-17:00 can be selected as the daily sampling moment.
And 104, inputting the historical photovoltaic power generation power of the historical sampling days at each sampling moment into a photovoltaic power generation power prediction model to obtain a photovoltaic power generation power prediction value of the prediction days at each sampling moment.
Here, the generated power prediction model is trained in advance. One exemplary embodiment of training the generated power prediction model is to obtain training data, wherein the training data comprises first photovoltaic power generation power of a first sample sampling day at each sampling time and second photovoltaic power generation power of a second sample sampling day at each sampling time, wherein the date of the second sample sampling day is later than the date of the first sample sampling day, the weather and the working condition of the photovoltaic power generation equipment of the second sample sampling day and the first sample sampling day are the same, the first photovoltaic power generation power of the first sample sampling day at each sampling time is used as the input of the initial power generation power prediction model, and the second photovoltaic power generation power of the second sample sampling day at each sampling moment is taken as the output of the initial power generation power prediction model, and training the generated power prediction model to obtain the trained generated power prediction model.
In some embodiments, the initial photovoltaic power generation power prediction model includes an input layer, a Convolutional Neural Networks (CNN) layer, a Long Short-Term Memory artificial Neural network (LSTM) layer, an attention attribute layer, and an output layer.
Wherein, the CNN layer comprises a convolution layer and a discard dropout layer.
In some exemplary embodiments, in order to improve computational efficiency, with the dropout layer set to 0.2, half of the hidden neurons in the network of the dropout layer may be temporarily randomly deleted, and the input-output neurons remain unchanged. It should be noted that the circles in fig. 2 represent non-deleted neurons, and the circles with crosses represent deleted neurons, as shown in fig. 2. And then, the input neurons are propagated forwards through the modified network, the obtained loss result is propagated backwards through the modified network, and the parameters (w, b) corresponding to the neurons which are not deleted are updated according to a random gradient descent method after a small batch of historical photovoltaic power generation power is executed.
It is understood that, after obtaining the updated corresponding parameters (w, b), in order to avoid the problem of overfitting of the trained photovoltaic power generation prediction model, in some embodiments, this process may be repeated continuously: recovering the deleted neurons, wherein the deleted neurons remain intact at this time, the non-deleted neurons are updated, a half-size subset is randomly selected from the hidden neurons to be temporarily deleted, parameters of the deleted neurons are backed up, and for a small batch of historical photovoltaic power generation power, the parameters (w, b) are updated according to a random gradient descent method after the loss is propagated forwards and backwards, so as to solve the problem of overfitting of different networks.
Where w is the parameter weight in the neural network and b is the bias in the neural network.
In other embodiments, in the case that the dropout layer is set to 0.2, if the number of neurons is n, then there may be 0.2n neurons to be deleted, wherein one embodiment of deleting neurons is to delete neuronsThe activation function value of an element in the network becomes 0 with probability p. If the output vector length is i, the target feature vector is Hc＝[hc1…hc1…]TWherein neurons of dropout compute activation function values in the network
One way of calculating is:
wherein, the Bernoulli function generates a probability vector r, that is, a vector of 0 and 1 is randomly generated.
The application provides a photovoltaic power generation power prediction method, which includes the steps of obtaining a prediction day, corresponding working conditions and weather data, historical sampling days with the working conditions and the weather data matched with the prediction day, and historical photovoltaic power generation power of the historical sampling days at each sampling moment, inputting the historical photovoltaic power generation power of the historical sampling days at each sampling moment into a photovoltaic power generation power prediction model, and accordingly obtaining a photovoltaic power generation power prediction value of the prediction day at each sampling moment. Therefore, in the process of predicting the photovoltaic power generation power, the photovoltaic power generation power of the historical sampling day matched with the prediction day is combined with the working condition and weather data to predict the photovoltaic power generation power of the prediction day, and the photovoltaic power generation power prediction value corresponding to the prediction day is accurately predicted through the photovoltaic power generation power prediction model.
Based on the above embodiment, the photovoltaic power generation power prediction model includes an input layer, a Convolutional Neural Networks (CNN) layer, a Long Short-Term Memory artificial Neural network (LSTM) layer, an attention attribute layer, and an output layer, and one embodiment of calculating the photovoltaic power generation power prediction value through the photovoltaic power generation power prediction model is that the collected historical photovoltaic power generation power is input to the input layer, is converted into an input vector, is subjected to feature extraction in the CNN layer, generates a target feature vector, and inputs the target feature vector to the LSTM layer, and the LSTM layer and the attribute layer predict the photovoltaic power generation power prediction value by learning a rule in the target feature vector extracted by the CNN layer, and outputs the prediction value through the output layer, as shown in fig. 3.
Fig. 4 is a schematic flowchart of another photovoltaic power generation power prediction method provided in an embodiment of the present application. It should be noted that, in this embodiment, a photovoltaic power generation power prediction model including an input layer, a CNN layer, an LSTM layer, an attention layer, and an output layer is described as an example. As shown in fig. 3, the method may include:
And step 403, acquiring historical photovoltaic power generation power of historical sampling days at each sampling moment.
It should be noted that, for a specific implementation manner of steps 401 to 403, reference may be made to the relevant description in the foregoing embodiments.
In some embodiments, after obtaining the historical photovoltaic power generation at each sampling time on the historical sampling day, the historical photovoltaic power generation is input into the input layer to obtain an input vector converted from the historical photovoltaic power generation, for example,if the historical photovoltaic power generation power length input in batches is m, the input vector is
In some embodiments, in order to accurately filter out the target feature vector, the CNN layer includes a convolution layer and a discard dropout layer, and one embodiment of inputting the input vector into the CNN layer and performing feature extraction on the input vector to filter out the target feature vector is as follows: inputting an input vector into the convolutional layer, acquiring a plurality of feature vectors of the input vector extracted by the convolutional layer, and inputting the plurality of feature vectors of the input vector into the dropout layer to screen out a target feature vector from the plurality of features.
In some exemplary embodiments, in the case that the data dimension of the photovoltaic power generation is 1 dimension, the convolution layer is selected as a one-dimensional convolution, and then the size of the convolution kernel is 3, and the RELU activation function is used in combination, so as to obtain a plurality of feature vectors of the input vector.
And 406, acquiring target feature vectors, and inputting the target feature vectors into the LSTM layer to obtain first output vectors corresponding to the target feature vectors.
In some embodiments, the obtained target feature vector is input into an LSTM layer, and the photovoltaic power generation power behavior characteristics are learned through the LSTM layer and a bidirectional Long-Term Memory artificial neural network (biLSTM) layer structure, and if the length of the first output vector is j, the first output vector of the LSTM layer is HL＝[hL1…hLε…hL]JCalculating HLOne way of calculating is:
Hl＝max(dropout(L))+br
wherein, LSTM layer needs to be connected to dropout layer and Max pooling Maxpooling layer, Max is maximum function in the Max pooling layer, br is bias of the pooling layer, L is output of the LSTM layer, W is output of the LSTM layer, and the maximum pooling layer is a function of maximum value in the Max pooling layerC,bcRespectively the weight and the bias of the LSTM layer.
In some embodiments, after the first output vectors corresponding to the target feature vectors are input to the attention layer, the attention weight parameter values of the first output vectors are distributed according to a weight distribution principle in the attention layer to obtain the attention weight parameter values of the first output vectors, and the first output vectors are filtered according to the attention weight parameter values of the first output vectors to obtain the second output vectors.
In some exemplary embodiments, if the length of the second output vector is k, the second output vector S' is
And step 408, inputting the second output vector into an output layer to obtain a photovoltaic power generation power predicted value of the predicted day at each sampling moment.
In some embodiments, after the second output vector is input to the output layer, the output layer obtains the predicted value of the power generation amount of the photovoltaic through the full-connection layer, and assuming that the predicted compensation of the output layer is n, the predicted value Y of the power generation amount of the photovoltaic is
An exemplary way to calculate Y is:
Y＝f(Wr·s+br)
wherein, WrAs output layer weights, brFor output layer biasing, f is the fully-connected layer activation function.
In other embodiments, after obtaining the predicted value of the photovoltaic power generation power, in order to accurately train the model, in some embodiments, the predicted value of the photovoltaic power generation power may be subjected to an inverse normalization process to obtain an actual predicted value subjected to the inverse normalization process.
An exemplary processing method of the denormalization processing is as follows:
wherein the content of the first and second substances,
the photovoltaic power generation power prediction data before the reverse normalization processing is obtained through the photovoltaic power generation power prediction network prediction, y is the photovoltaic power generation power prediction value after the reverse normalization processing, ymin、ymaxThe minimum value and the maximum value in the historical output data before normalization processing are respectively.
The application provides a method for predicting photovoltaic power generation power, which comprises the steps of inputting historical photovoltaic power generation power into an input layer by obtaining a prediction day, corresponding working conditions and weather data, historical sampling days with the working conditions and the weather data matched with the prediction day and the historical photovoltaic power generation power of the historical sampling days at each sampling moment to obtain input vectors corresponding to the historical photovoltaic power generation power, inputting the input vectors into a CNN layer, extracting the characteristics of the input vectors to screen out target characteristic vectors, inputting the target characteristic vectors into an LSTM layer to obtain first output vectors corresponding to the target characteristic vectors, inputting the first output vectors corresponding to the target characteristic vectors into an attention layer, and screening the first output vectors according to attention weight parameter values of the first output vectors in the attention layer, to obtain a second output vector, and inputting the second output vector to the output layer to determine a predicted value of the photovoltaic power generation power and output the predicted value of the photovoltaic power generation power. Therefore, in the process of predicting the photovoltaic power generation power, the photovoltaic power generation power of the historical sampling day matched with the prediction day is predicted by combining the working condition and the weather data, so that the photovoltaic power generation power of the prediction day is predicted, and the photovoltaic power generation power prediction model can more accurately predict the photovoltaic power generation power prediction value corresponding to the prediction day.
Fig. 5 is a schematic structural diagram of a device for predicting photovoltaic power generation provided in an embodiment of the present application.
As shown in fig. 5, the photovoltaic power generation prediction apparatus 500 includes:
the first obtaining module 501 is configured to obtain a predicted day and corresponding working conditions and weather data.
A second obtaining module 502 is configured to obtain historical sampling days for which the working condition and weather data match the predicted days.
And a third obtaining module 503, configured to obtain historical photovoltaic power generation power at each sampling time on a historical sampling day.
The generating module 504 is configured to input the historical photovoltaic power generation power at each sampling time of the historical sampling day into the photovoltaic power generation power prediction model, so as to obtain a photovoltaic power generation power predicted value at each sampling time of the prediction day.
The application provides a photovoltaic power generation power prediction device, which is used for obtaining a prediction day, corresponding working conditions and weather data, historical sampling days matched with the prediction day according to the working conditions and the weather data, and historical photovoltaic power generation power of the historical sampling days at each sampling moment, inputting the historical photovoltaic power generation power of the historical sampling days at each sampling moment into a photovoltaic power generation power prediction model, and obtaining a photovoltaic power generation power prediction value of the prediction day at each sampling moment. Therefore, in the process of predicting the photovoltaic power generation power, the photovoltaic power generation power of the historical sampling day matched with the prediction day is combined with the working condition and weather data to predict the photovoltaic power generation power of the prediction day, and the photovoltaic power generation power prediction value corresponding to the prediction day is accurately predicted through the photovoltaic power generation power prediction model.
In an embodiment of the present application, as shown in fig. 6, the photovoltaic power generation power prediction model includes an input layer, a convolutional neural network CNN layer, a long-short term memory artificial neural network LSTM layer, an attention layer, and an output layer, and the generation module 504 includes:
the input unit 5041 is configured to input historical photovoltaic power generation power of the historical sampling day at each sampling time to an input layer, and obtain input vectors corresponding to the historical photovoltaic power generation power through the input layer.
An extracting unit 5042, configured to input the input vector to the CNN layer, and perform feature extraction on the input vector to filter out a target feature vector.
The first generating unit 5043 is configured to obtain target feature vectors, and input the target feature vectors into the LSTM layer to obtain first output vectors corresponding to the target feature vectors.
The second generating unit 5044 is configured to input the first output vectors corresponding to the target feature vectors into the attention layer, and filter the first output vectors according to the attention weight parameter values of the first output vectors in the attention layer to obtain second output vectors.
And the output unit 5045 is used for inputting the second output vector to the output layer so as to obtain the photovoltaic power generation power predicted value of the prediction day at each sampling moment.
In one embodiment of the present application, as shown in fig. 6, the CNN layer includes convolution and dropout layers, and the extraction unit 5042 is specifically configured to:
the input vector is input into the convolutional layer, and a plurality of feature vectors of the input vector extracted by the convolutional layer are obtained.
And inputting a plurality of feature vectors of the input vector into a dropout layer to screen out a target feature vector from the plurality of features.
In an embodiment of the present application, as shown in fig. 6, the generating module 504 further includes:
and the processing unit 5046 is configured to perform inverse normalization processing on the photovoltaic power generation power predicted value at each sampling time on the predicted day.
The application provides a photovoltaic power generation power prediction device, which is used for obtaining a prediction day, corresponding working conditions and weather data, historical sampling days matched with the prediction day according to the working conditions and the weather data, and historical photovoltaic power generation power of the historical sampling days at each sampling moment, inputting the historical photovoltaic power generation power of the historical sampling days at each sampling moment into a photovoltaic power generation power prediction model, and obtaining a photovoltaic power generation power prediction value of the prediction day at each sampling moment. Therefore, in the process of predicting the photovoltaic power generation power, the photovoltaic power generation power of the historical sampling day matched with the prediction day is combined with the working condition and weather data to predict the photovoltaic power generation power of the prediction day, and the photovoltaic power generation power prediction value corresponding to the prediction day is accurately predicted through the photovoltaic power generation power prediction model.
FIG. 7 is a block diagram of an electronic device according to an embodiment of the present application.
As shown in fig. 7, the electronic apparatus includes:
The instructions executed by the processor 702 implement the photovoltaic power generation prediction method provided in the above-described embodiments.
Further, the electronic device further includes:
a communication interface 703 for communication between the memory 701 and the processor 702.
A memory 701 for storing computer instructions executable on the processor 702.
The memory 701 may comprise high-speed RAM memory, and may also include non-volatile memory (non-volatile memory), such as at least one disk memory.
And a processor 702, configured to implement the photovoltaic power generation power prediction method according to the foregoing embodiment when executing a program.
If the memory 701, the processor 702 and the communication interface 703 are implemented independently, the communication interface 703, the memory 701 and the processor 702 may be connected to each other through a bus and perform communication with each other. The bus may be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, an Extended ISA (EISA) bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc. For ease of illustration, only one thick line is shown in FIG. 7, but this is not intended to represent only one bus or type of bus.
Optionally, in a specific implementation, if the memory 701, the processor 702, and the communication interface 703 are integrated on a chip, the memory 701, the processor 702, and the communication interface 703 may complete mutual communication through an internal interface.
The processor 702 may be a Central Processing Unit (CPU), an Application Specific Integrated Circuit (ASIC), or one or more Integrated circuits configured to implement embodiments of the present Application.
Furthermore, the terms "first", "second" and "first" are used for descriptive purposes only and are not to be construed as indicating or implying relative importance or implicitly indicating the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include at least one such feature. In the description of the present application, "plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
In the description herein, reference to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., means that a particular feature, structure, material, or characteristic described in connection with the embodiment or example is included in at least one embodiment or example of the application. In this specification, the schematic representations of the terms used above are not necessarily intended to refer to the same embodiment or example. Furthermore, the particular features, structures, materials, or characteristics described may be combined in any suitable manner in any one or more embodiments or examples. Furthermore, various embodiments or examples and features of different embodiments or examples described in this specification can be combined and combined by one skilled in the art without contradiction.
Although embodiments of the present application have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present application, and that variations, modifications, substitutions and alterations may be made to the above embodiments by those of ordinary skill in the art within the scope of the present application.
Claims (10)
1. A method for predicting photovoltaic power generation power is characterized by comprising the following steps:
acquiring a predicted day and corresponding working condition and weather data;
acquiring historical sampling days matched with the working condition and weather data and the prediction days;
acquiring historical photovoltaic power generation power of the historical sampling days at each sampling moment;
and inputting the historical photovoltaic power generation power of the historical sampling days at each sampling moment into a photovoltaic power generation power prediction model to obtain the photovoltaic power generation power prediction value of the prediction days at each sampling moment.
2. The method of claim 1, wherein the photovoltaic power generation power prediction model comprises an input layer, a Convolutional Neural Network (CNN) layer, a long-short term memory artificial neural network (LSTM) layer, an attention layer and an output layer, and the inputting the historical photovoltaic power generation power of the historical sampling days at each sampling time into the photovoltaic power generation power prediction model to obtain the photovoltaic power generation power prediction value of the prediction days at each sampling time comprises:
inputting the historical photovoltaic power generation power of the historical sampling days at each sampling moment into the input layer, and obtaining input vectors corresponding to the historical photovoltaic power generation power through the input layer;
inputting the input vector into the CNN layer, and performing feature extraction on the input vector to screen out a target feature vector;
acquiring the target characteristic vectors, and inputting the target characteristic vectors into the LSTM layer to obtain first output vectors corresponding to the target characteristic vectors respectively;
inputting first output vectors corresponding to the target feature vectors into the attention layer, and screening the first output vectors according to attention weight parameter values of the first output vectors in the attention layer to obtain second output vectors;
and inputting the second output vector into the output layer to obtain a photovoltaic power generation power predicted value of the predicted day at each sampling moment.
3. The method of claim 2, wherein the CNN layers include convolutional layers and discard dropout layers, inputting the input vector to the CNN layers, and performing feature extraction on the input vector to filter out a target feature vector, comprises:
inputting the input vector into the convolutional layer to obtain a plurality of characteristic vectors of the input vector extracted by the convolutional layer;
inputting a plurality of feature vectors of the input vector into the dropout layer to screen out a target feature vector from the plurality of features.
4. The method of claim 2, further comprising, after inputting the second output vector to the output layer to obtain predicted photovoltaic power generation power values for the predicted day at respective sampling times:
and carrying out reverse normalization processing on the photovoltaic power generation power predicted value of the prediction day at each sampling moment.
5. An apparatus for predicting photovoltaic power generation power, the apparatus comprising:
the first acquisition module is used for acquiring the predicted day and corresponding working condition and weather data;
the second acquisition module is used for acquiring historical sampling days matched with the working condition and weather data and the prediction days;
the third acquisition module is used for acquiring historical photovoltaic power generation power of the historical sampling days at each sampling moment;
and the generation module is used for inputting the historical photovoltaic power generation power of the historical sampling days at each sampling moment into a photovoltaic power generation power prediction model so as to obtain the photovoltaic power generation power prediction value of the prediction days at each sampling moment.
6. The apparatus of claim 5, wherein the photovoltaic power generation power prediction model comprises an input layer, a Convolutional Neural Network (CNN) layer, a long-short term memory artificial neural network (LSTM) layer, an attention layer, and an output layer, and the generating module comprises:
the input unit is used for inputting the historical photovoltaic power generation power of the historical sampling day at each sampling moment into the input layer and obtaining input vectors corresponding to the historical photovoltaic power generation power through the input layer;
the extraction unit is used for inputting the input vector into the CNN layer and extracting the characteristics of the input vector to screen out a target characteristic vector;
the first generating unit is used for acquiring the target characteristic vectors and inputting the target characteristic vectors into the LSTM layer to obtain first output vectors corresponding to the target characteristic vectors;
a second generating unit, configured to input first output vectors corresponding to the target feature vectors into the attention layer, and filter the first output vectors according to attention weight parameter values of the first output vectors in the attention layer to obtain second output vectors;
and the output unit is used for inputting the second output vector into the output layer so as to obtain the photovoltaic power generation power predicted value of the predicted day at each sampling moment.
7. The apparatus of claim 6, wherein the CNN layers comprise convolutional layers and discard dropout layers, the extraction unit to:
inputting the input vector into the convolutional layer to obtain a plurality of characteristic vectors of the input vector extracted by the convolutional layer;
inputting a plurality of feature vectors of the input vector into the dropout layer to screen out a target feature vector from the plurality of features.
8. The apparatus of claim 6, wherein the generating module further comprises:
and the processing unit is used for carrying out inverse normalization processing on the photovoltaic power generation power predicted value of the predicted day at each sampling moment.
9. An electronic device, comprising:
memory, processor and computer program stored on the memory and executable on the processor, characterized in that the processor, when executing the program, implements the method of predicting photovoltaic power generation as claimed in any one of claims 1 to 4.
10. A computer-readable storage medium, on which a computer program is stored, which program, when being executed by a processor, is adapted to carry out the method of predicting photovoltaic power generation according to any one of claims 1 to 4.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111374757.3A CN114254556A (en) | 2021-11-17 | 2021-11-17 | Photovoltaic power generation power prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111374757.3A CN114254556A (en) | 2021-11-17 | 2021-11-17 | Photovoltaic power generation power prediction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114254556A true CN114254556A (en) | 2022-03-29 |
Family
ID=80792745
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111374757.3A Pending CN114254556A (en) | 2021-11-17 | 2021-11-17 | Photovoltaic power generation power prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114254556A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115630726A (en) * | 2022-09-01 | 2023-01-20 | 华能江苏综合能源服务有限公司 | Roof photovoltaic power prediction method based on VMD-BILSTM neural network fusion attention mechanism |
| CN115660032A (en) * | 2022-08-31 | 2023-01-31 | 华能江苏综合能源服务有限公司 | Building roof photovoltaic power prediction method based on BI-LSTM neural network fusion attention mechanism |
| CN116565863A (en) * | 2023-07-10 | 2023-08-08 | 南京师范大学 | Short-term photovoltaic output prediction method based on space-time correlation |
-
2021
- 2021-11-17 CN CN202111374757.3A patent/CN114254556A/en active Pending
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115660032A (en) * | 2022-08-31 | 2023-01-31 | 华能江苏综合能源服务有限公司 | Building roof photovoltaic power prediction method based on BI-LSTM neural network fusion attention mechanism |
| CN115660032B (en) * | 2022-08-31 | 2024-05-10 | 华能江苏综合能源服务有限公司 | BI-LSTM neural network integration attention mechanism-based building roof photovoltaic power prediction method |
| CN115630726A (en) * | 2022-09-01 | 2023-01-20 | 华能江苏综合能源服务有限公司 | Roof photovoltaic power prediction method based on VMD-BILSTM neural network fusion attention mechanism |
| CN115630726B (en) * | 2022-09-01 | 2024-01-30 | 华能江苏综合能源服务有限公司 | Roof photovoltaic power prediction method based on VMD-BILSTM neural network fused attention mechanism |
| CN116565863A (en) * | 2023-07-10 | 2023-08-08 | 南京师范大学 | Short-term photovoltaic output prediction method based on space-time correlation |
| CN116565863B (en) * | 2023-07-10 | 2023-09-26 | 南京师范大学 | Short-term photovoltaic output prediction method based on space-time correlation |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN114254556A (en) | Photovoltaic power generation power prediction method and device, electronic equipment and storage medium | |
| US20210042580A1 (en) | Model training method and apparatus for image recognition, network device, and storage medium | |
| CN112101190B (en) | Remote sensing image classification method, storage medium and computing device | |
| CN110874550A (en) | Data processing method, device, equipment and system | |
| JP7020547B2 (en) | Information processing equipment, control methods, and programs | |
| CN113657421B (en) | Convolutional neural network compression method and device, and image classification method and device | |
| Song et al. | Short-term forecasting based on graph convolution networks and multiresolution convolution neural networks for wind power | |
| CN114283320B (en) | Branch-free structure target detection method based on full convolution | |
| CN113536144A (en) | Social network information propagation scale prediction method and device | |
| CN116316591A (en) | Short-term photovoltaic power prediction method and system based on hybrid bidirectional gating cycle | |
| CN114241230A (en) | Target detection model pruning method and target detection method | |
| CN111368887A (en) | Training method of thunderstorm weather prediction model and thunderstorm weather prediction method | |
| CN114282666A (en) | Structured pruning method and device based on local sparse constraint | |
| CN112766603A (en) | Traffic flow prediction method, system, computer device and storage medium | |
| CN114417739B (en) | Method and device for recommending process parameters under abnormal working conditions | |
| CN113609763B (en) | Uncertainty-based satellite component layout temperature field prediction method | |
| CN114330705A (en) | Photovoltaic power generation capacity prediction method and device, electronic equipment and storage medium | |
| CN111368150B (en) | Training method and device of prediction model and electronic equipment | |
| CN115791180A (en) | Alarm method and device for fan bearing vibration | |
| CN109697511B (en) | Data reasoning method and device and computer equipment | |
| CN115131646A (en) | Deep network model compression method based on discrete coefficient | |
| CN112149351B (en) | Microwave circuit physical dimension estimation method based on deep learning | |
| CN114239945A (en) | Short-term power load prediction method, device, equipment and storage medium | |
| AU2020278885A1 (en) | Neural network execution block using fully connected layers | |
| CN114298370A (en) | Photovoltaic power generation capacity prediction method and device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |