CN114330495A - Wind power prediction method and device based on deep learning fusion model - Google Patents

Wind power prediction method and device based on deep learning fusion model Download PDF

Info

Publication number
CN114330495A
CN114330495A CN202111424160.5A CN202111424160A CN114330495A CN 114330495 A CN114330495 A CN 114330495A CN 202111424160 A CN202111424160 A CN 202111424160A CN 114330495 A CN114330495 A CN 114330495A
Authority
CN
China
Prior art keywords
wind power
data
prediction
real
module
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
Application number
CN202111424160.5A
Other languages
Chinese (zh)
Inventor
曾谁飞
王振荣
傅望安
黄思皖
王青天
张燧
刘旭亮
李小翔
冯帆
邸智
韦玮
童彤
任鑫
杜静宇
赵鹏程
武青
祝金涛
朱俊杰
吴昊
吕亮
段周期
胡雪琛
项灵文
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Huaneng Clean Energy Research Institute
Original Assignee
Huaneng Clean Energy Research Institute
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Huaneng Clean Energy Research Institute filed Critical Huaneng Clean Energy Research Institute
Priority to CN202111424160.5A priority Critical patent/CN114330495A/en
Publication of CN114330495A publication Critical patent/CN114330495A/en
Priority to PCT/CN2022/099615 priority patent/WO2023093010A1/en
Pending legal-status Critical Current

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/04—Architecture, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computing arrangements based on biological models
    • G06N3/02—Neural networks
    • G06N3/08—Learning methods
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
    • G06Q50/06—Electricity, gas or water supply

Abstract

The invention provides a wind power prediction method and device based on a deep learning fusion model, which are used for predicting wind power by utilizing Scada system wind power real-time monitoring data and combining historical wind power data, inputting the Scada system wind power real-time monitoring data and the historical wind power data into a deep learning fusion model constructed by a convolutional neural network, a BiLSTM network and an Attention mechanism to extract text features, and finally performing merging operation on the obtained features to obtain fusion features, so that the optimal text features are obtained to perform efficient and accurate prediction on the wind power. By the method, the accuracy of making the scheduling operation plan of the power supply system is improved, and the error phenomenon of new energy power generation power prediction is reduced.

Description

Wind power prediction method and device based on deep learning fusion model
Technical Field
The invention relates to the technical fields of artificial intelligence, deep learning, natural language processing, new energy and carbon neutralization and carbon peak-to-peak, in particular to a wind power prediction method and device based on a deep learning fusion model, computer equipment and a storage medium.
Background
With the rapid development of the deep learning fusion model and the scheduling operation of the wind power system, a greater challenge is provided for the wind power prediction accuracy, such as: the new visual angle of wind power accurate prediction is optimized from two dimensions of real-time data and historical wind power data of an SCADA system, and a reliable decision basis is provided for the formulation of a wind power supply plan and the safe operation. The current wind power prediction method comprises a physical method, a statistical method, a single network model deep learning method and the like, but the methods have the defects that the wind power prediction is insufficient and inaccurate, and the defects are represented as follows: the method considers that the acquired data is insufficient and can cause an overfitting phenomenon, or the dimensionality reduction effect is not obvious, or a neural network model of a single space-time data characteristic is constructed, and the context information, the dimensionality reduction or compression of the data, the extraction of text characteristics by combining multiple dimensions and the like are not considered. Therefore, if the accurate prediction of the wind power is not solved, many disadvantages are brought to the power supply system, including not only increasing various operation costs, indirectly increasing expenses such as manpower, and even forming the safe operation of the power dispatching system.
Disclosure of Invention
The invention provides a wind power prediction method and device based on a deep learning fusion model, computer equipment and a storage medium, and aims to improve the formulation accuracy of a power supply system scheduling operation plan and reduce the error phenomenon of new energy power generation prediction.
To this end, a first object of the present invention is to provide a deep learning photovoltaic short-term power prediction method, including:
acquiring wind power real-time monitoring data and historical wind power data in a specified time interval, preprocessing the data, and taking the preprocessed wind power real-time monitoring data and the historical wind power data as training sets;
constructing a wind power prediction network model, and training the constructed wind power prediction network model through a training set; the wind power prediction network model comprises a feature extraction module, a context information extraction module, a key information prediction module, a feature fusion module and a result prediction module which are connected in sequence;
and preprocessing the real-time monitoring data of the wind power generated in real time and the historical wind power data, inputting the preprocessed data into a trained wind power prediction network model, and outputting a result as a prediction result of the wind power in a future specified time interval.
Wherein, the data preprocessing step comprises:
and (3) data format analysis: analyzing the data formats of the wind power real-time monitoring data and/or historical wind power data in different data formats taken from the SCADA system, and converting the data formats into a unified format;
analyzing data correlation to eliminate wind power real-time monitoring data and historical wind power data with the weight lower than a set threshold;
normalization processing, namely normalizing the wind power real-time monitoring data and the historical wind power data according to a formula (1);
Figure BDA0003378407180000021
where w' is a normalized value, w represents the true value of the sample, wminAnd wmaxRepresenting the minimum and maximum values selected.
The wind power prediction network model comprises a feature extraction module, a context information extraction module, a key information prediction module, a feature fusion module and a result prediction module which are connected in sequence; wherein the content of the first and second substances,
the characteristic extraction module is a characteristic extraction neural network and is used for extracting characteristics of the wind power real-time monitoring data and the historical wind power data to obtain corresponding text space-time characteristics;
the context information extraction module is used for acquiring the sequence relation of the wind power real-time monitoring data and the historical wind power data on a time sequence to obtain the context information of the wind power real-time monitoring data and the historical wind power data;
the key information prediction module is used for acquiring interactive characteristics in the mined wind power real-time monitoring data and historical wind power data, and forming context characteristics of the wind power real-time monitoring data and the historical wind power data with key prediction information;
the characteristic fusion module is used for fusing and splicing the context characteristics of the wind power real-time monitoring data and the historical wind power data to obtain characteristic fusion information;
and the result prediction module is used for calculating a prediction result according to the feature fusion information to complete wind power prediction.
The characteristic extraction neural network is a convolutional neural network model CNN network; the convolutional neural network model CNN network comprises 1 convolutional layer and 1 pooling layer, and high-frequency space-time characteristics are obtained by adopting a maximum pooling method.
The context information extraction module adopts a BilSTM network model, inputs high-frequency space-time characteristics into the BilSTM network model, outputs context relationships of data at different moments, and performs redundant information filtering function by using a forgetting gate of the BilSTM network model to improve text characteristic representation and fitting capability.
The key information prediction module obtains different weights in the features according to the real-time wind power monitoring data and the historical wind power data by utilizing a self-attention and interactive attention mechanism in bidirectional attention, and the interactivity characteristics in the features of the two data are mined, so that the context features with the key prediction information are formed finally.
The method comprises the following steps of constructing a wind power prediction network model through a training set, wherein the steps of training the constructed wind power prediction network model through the training set comprise:
inputting the preprocessed training set data into a feature extraction neural network of a feature extraction module, and performing feature extraction through a convolutional neural network model (CNN) network;
obtaining a sequence relation of a past moment and a future moment by using a BilSTM network model so as to obtain context information;
respectively acquiring context characteristics with key prediction information from real-time wind power monitoring data and historical wind power data by utilizing a self-attention and interactive attention mechanism in bidirectional attention, mining interactive characteristics in the characteristics of the two kinds of data, and respectively forming interactive characteristics of the two kinds of data containing the context information;
the interactive characteristics containing the context information are combined to obtain fusion characteristics, the fusion characteristics contain the context information and the interactive characteristics, and the contribution degree of real-time data and historical data to wind power prediction is fully reflected;
and calculating a prediction result by using the full connection layer, comparing the prediction result with a marked detection result, and finishing network training by continuously adjusting network functions and parameters until the prediction result is consistent with an actual power result.
After the step of outputting the prediction result of the wind power, the method also comprises a step of displaying the result; wherein, the result display mode at least comprises: the method comprises the following steps of character display, voice broadcast, terminal outbound, mail and short message transmission, intelligent sound box and voice awakening.
The second objective of the present invention is to provide a wind power prediction device based on a deep learning fusion model, which includes:
the data processing module is used for acquiring wind power real-time monitoring data and historical wind power data in a specified time interval, preprocessing the data and taking the preprocessed wind power real-time monitoring data and the historical wind power data as a training set;
the network construction module is used for constructing a wind power prediction network model and training the constructed wind power prediction network model through a training set; the wind power prediction network model comprises a feature extraction module, a context information extraction module, a key information prediction module, a feature fusion module and a result prediction module which are connected in sequence;
and the power prediction module is used for preprocessing the real-time monitoring data of the wind power generated in real time and the historical wind power data, inputting the preprocessed data into the trained wind power prediction network model, and outputting a result as a prediction result of the wind power in a future specified time interval.
A third object of the present invention is to provide a computer device, which includes a memory, a processor and a computer program stored in the memory and running on the processor, wherein the processor executes the computer program to implement the method according to the foregoing technical solution.
A fourth object of the invention is to propose a non-transitory computer-readable storage medium on which a computer program is stored, which computer program, when executed by a processor, implements the method of the aforementioned technical solution.
The method for predicting the wind power based on the deep learning fusion model is characterized in that real-time monitoring data of the wind power of the Scada system and historical wind power data are utilized to predict the wind power, the real-time monitoring data of the wind power of the Scada system and the historical wind power data are input into a deep learning fusion model constructed by a convolutional neural network, a BilStm network and an Attention mechanism to extract text features, and finally the obtained features are combined to obtain fusion features, so that the optimal text features are obtained to efficiently and accurately predict the wind power. By the method, the accuracy of making the scheduling operation plan of the power supply system is improved, and the error phenomenon of new energy power generation power prediction is reduced.
Drawings
The foregoing and/or additional aspects and advantages of the present invention will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic flow diagram of a wind power prediction method based on a deep learning fusion model provided by the invention.
FIG. 2 is a schematic structural diagram of a wind power prediction network model of a wind power prediction method based on a deep learning fusion model provided by the invention.
FIG. 3 is a schematic structural diagram of a wind power prediction device based on a deep learning fusion model provided by the invention.
Fig. 4 is a schematic structural diagram of a non-transitory computer-readable storage medium according to the present invention.
Detailed Description
Reference will now be made in detail to embodiments of the present invention, 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 illustrative and intended to be illustrative of the invention and are not to be construed as limiting the invention.
Fig. 1 is a schematic flow diagram of a wind power prediction method based on a deep learning fusion model according to an embodiment of the present invention. The method comprises the following steps:
step 101, acquiring wind power real-time monitoring data and historical wind power data in a specified time interval, preprocessing the data, and taking the preprocessed wind power real-time monitoring data and the historical wind power data as a training set.
The invention constructs a deep learning prediction model with multi-scale convolution kernel CNN + BiLSTM + bidirectional Attention, aiming at the problems that overfitting phenomenon is caused by insufficient characteristics of extracted wind power real-time monitoring data and historical wind power data, wind power prediction accuracy is inaccurate, and the like.
Firstly, acquiring data from a Scada system database, and extracting wind power real-time monitoring data in a specified time interval and historical wind power data; in the invention, the time interval of the wind power real-time monitoring data can be 24 hours, and the historical wind power data is data within one year from the time limit of the wind power real-time monitoring data.
After the data acquisition is completed, the method further includes a step of data preprocessing, as shown in 101 in fig. 2:
and (3) data format analysis: and analyzing the data formats of the wind power real-time monitoring data and/or the historical wind power data in different data formats, and converting the data formats into a unified format.
And analyzing the data correlation to eliminate the wind power real-time monitoring data and the historical wind power data with the weight lower than a set threshold.
And (4) normalization processing, namely normalizing the wind power real-time monitoring data and the historical wind power data according to a formula (1).
Figure BDA0003378407180000051
Where w' is a normalized value, w represents the true value of the sample, wminAnd wmaxRepresenting the minimum and maximum values selected.
After the data preprocessing is completed, the process proceeds to step 102.
Step 102: and constructing a wind power prediction network model, and training the constructed wind power prediction network model through a training set. As shown in fig. 2, the wind power prediction network model includes a feature extraction module 102, a context information extraction module 103, a key information prediction module 104, a feature fusion module 105, and a result prediction module 106, which are connected in sequence.
The feature extraction module 102 is a feature extraction neural network, and is used for performing feature extraction on the wind power real-time monitoring data and the historical wind power data to obtain corresponding text space-time features; the characteristic extraction neural network is a convolutional neural network model CNN network; the convolutional neural network model CNN network comprises 1 convolutional layer and 1 pooling layer, and the maximum pooling method is adopted, so that high-frequency space-time characteristics can be better extracted, unified dimension reduction and compression of the two data are facilitated, and a universal fitting phenomenon is optimized, so that the space-time characteristic extraction of the two data is completed. And respectively inputting the wind power real-time monitoring data and the historical wind power data into a CNN network model to obtain high-frequency space-time characteristics.
The context information extraction module 103 is configured to obtain a sequence relation between the real-time wind power monitoring data and the historical wind power data in a time sequence, and obtain context information between the real-time wind power monitoring data and the historical wind power data; the context information extraction module adopts a BilSTM network model, inputs high-frequency space-time characteristics into the BilSTM network model, outputs context relations of data at different moments, and utilizes a forgetting gate of the BilSTM network model to perform redundant information filtering function, thereby improving text characteristic representation and fitting capability.
The key information prediction module 104 is used for acquiring interactive characteristics of the mined wind power real-time monitoring data and the historical wind power data, and forming context characteristics of the wind power real-time monitoring data and the historical wind power data with key prediction information; the key information prediction module obtains different weights inside the features according to the real-time wind power monitoring data and the historical wind power data by utilizing a self-attention and interactive attention mechanism in bidirectional attention, and the interactivity characteristics inside the features of the two data are mined, so that the context features with the key prediction information are formed finally.
The feature fusion module 105 is used for fusion and splicing context features of the wind power real-time monitoring data and the historical wind power data to obtain feature fusion information; the fusion feature contains the contribution degree of past historical data to wind power prediction.
And the result prediction module 106 is used for calculating a prediction result according to the feature fusion information to complete wind power prediction.
The step of training the constructed wind power prediction network model through the training set comprises the following steps:
inputting the preprocessed training set data into a feature extraction neural network of the feature extraction module 102, and performing feature extraction through a convolutional neural network model (CNN) network;
obtaining a sequence relation of a past moment and a future moment by using a BilSTM network model so as to obtain context information;
respectively acquiring context characteristics with key prediction information from real-time wind power monitoring data and historical wind power data by utilizing a self-attention and interactive attention mechanism in bidirectional attention, mining interactive characteristics in the characteristics of the two kinds of data, and respectively forming interactive characteristics of the two kinds of data containing the context information;
the interactive characteristics containing the context information are combined to obtain fusion characteristics, the fusion characteristics contain the context information and the interactive characteristics, and the contribution degree of real-time data and historical data to wind power prediction is fully reflected;
and calculating a prediction result by using the full connection layer, comparing the prediction result with a marked detection result, and finishing network training by continuously adjusting network functions and parameters until the prediction result is consistent with an actual power result.
The wind power prediction value is calculated through the full connection layer, an activation function ReLU function is used as a Dense activation function, the prediction result obtained through calculation is calculated through a normalization reduction function, and the original size of the prediction result is obtained.
S103: and preprocessing the real-time monitoring data of the wind power generated in real time and the historical wind power data, inputting the preprocessed data into a trained wind power prediction network model, and outputting a result as a prediction result of the photovoltaic power in a future specified time interval.
The mean absolute error MAE and the root mean square error RMSE of the system are reduced by historical power data within 1 year and monitoring data acquired in real time within 24 hours, and the method has important significance for improving a photovoltaic short-term power prediction model and scheduling operation and photovoltaic proportion of a power system.
The invention selects the mean absolute error MAE and the root mean square error RMSE.
Wo＝Wpre(wmax-Wmin)+wmin (2)
Wherein wprePredicting an output value, W, for a network modeloRepresenting the restored power prediction.
After the step of outputting the prediction result of the wind power, the method also comprises a step of displaying the result; wherein, the result display mode at least comprises: the method comprises the following steps of character display, voice broadcast, terminal outbound, mail and short message transmission and intelligent sound box voice awakening.
In order to implement the above embodiment, the present invention further provides a wind power prediction apparatus based on a deep learning fusion model, including:
the data acquisition module 310 is configured to acquire wind power real-time monitoring data within a specified time interval, acquire historical wind power data at the same time, perform data preprocessing, and use the preprocessed wind power real-time monitoring data and the historical wind power data as a training set;
the network construction module 320 is used for constructing a wind power prediction network model and training the constructed wind power prediction network model through a training set; the wind power prediction network model comprises a feature extraction module, a context information extraction module, a key information prediction module, a feature fusion module and a result prediction module which are connected in sequence;
and the power prediction module 330 is configured to input the wind power real-time monitoring data and the historical wind power data generated in real time into the trained wind power prediction network model after preprocessing, and output a result as a prediction result of the wind power within a future specified time interval.
In order to implement the above embodiment, the present invention further provides another computer device, including: the wind power prediction device comprises a memory, a processor and a computer program which is stored on the memory and can run on the processor, wherein when the processor executes the computer program, the wind power prediction device realizes the wind power prediction according to the embodiment of the invention.
As shown in fig. 4, the non-transitory computer readable storage medium includes a memory 810 of instructions executable by a processor 820 of a deep learning fusion model based wind power prediction apparatus to perform the above-described method, and an interface 830. Alternatively, the storage medium may be a non-transitory computer readable storage medium, for example, the non-transitory computer readable storage medium may be a ROM, a Random Access Memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, and the like.
In order to achieve the above embodiments, the present invention further proposes a non-transitory computer readable storage medium having stored thereon a computer program, which when executed by a processor, implements wind power prediction according to an embodiment of the present invention.
In the description herein, references to the description of the term "one embodiment," "some embodiments," "an example," "a specific example," or "some examples," etc., mean 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 invention. 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.
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 invention, "a plurality" means at least two, e.g., two, three, etc., unless specifically limited otherwise.
Any process or method descriptions in flow charts or otherwise described herein may be understood as representing modules, segments, or portions of code which include one or more executable instructions for implementing steps of a custom logic function or process, and alternate implementations are included within the scope of the preferred embodiment of the present invention in which functions may be executed out of order from that shown or discussed, including substantially concurrently or in reverse order, depending on the functionality involved, as would be understood by those reasonably skilled in the art of the present invention.
The logic and/or steps represented in the flowcharts or otherwise described herein, e.g., an ordered listing of executable instructions that can be considered to implement logical functions, can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, processor-containing system, or other system that can fetch the instructions from the instruction execution system, apparatus, or device and execute the instructions. For the purposes of this description, a "computer-readable medium" can be any means that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device. More specific examples (a non-exhaustive list) of the computer-readable medium would include the following: an electrical connection (electronic device) having one or more wires, a portable computer diskette (magnetic device), a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium could even be paper or another suitable medium upon which the program is printed, as the program can be electronically captured, via for instance optical scanning of the paper or other medium, then compiled, interpreted or otherwise processed in a suitable manner if necessary, and then stored in a computer memory.
It should be understood that portions of the present invention may be implemented in hardware, software, firmware, or a combination thereof. In the above embodiments, the various steps or methods may be implemented in software or firmware stored in memory and executed by a suitable instruction execution system. If implemented in hardware, as in another embodiment, any one or combination of the following techniques, which are known in the art, may be used: a discrete logic circuit having a logic gate circuit for implementing a logic function on a data signal, an application specific integrated circuit having an appropriate combinational logic gate circuit, a Programmable Gate Array (PGA), a Field Programmable Gate Array (FPGA), or the like.
It will be understood by those skilled in the art that all or part of the steps carried by the method for implementing the above embodiments may be implemented by hardware related to instructions of a program, which may be stored in a computer readable storage medium, and when the program is executed, the program includes one or a combination of the steps of the method embodiments.
In addition, functional units in the embodiments of the present invention may be integrated into one processing module, or each unit may exist alone physically, or two or more units are integrated into one module. The integrated module can be realized in a hardware mode, and can also be realized in a software functional module mode. The integrated module, if implemented in the form of a software functional module and sold or used as a stand-alone product, may also be stored in a computer readable storage medium.
The storage medium mentioned above may be a read-only memory, a magnetic or optical disk, etc. Although embodiments of the present invention have been shown and described above, it is understood that the above embodiments are exemplary and should not be construed as limiting the present invention, and that variations, modifications, substitutions and alterations can be made to the above embodiments by those of ordinary skill in the art within the scope of the present invention.

Claims (11)

1. A wind power prediction method based on a deep learning fusion model is characterized by comprising the following steps:
acquiring wind power real-time monitoring data and historical wind power data in a specified time interval, preprocessing the data, and taking the preprocessed wind power real-time monitoring data and the historical wind power data as training sets;
constructing a wind power prediction network model, and training the constructed wind power prediction network model through the training set; the wind power prediction network model comprises a feature extraction module, a context information extraction module, a key information prediction module, a feature fusion module and a result prediction module which are connected in sequence;
preprocessing the real-time monitoring data of the wind power generated in real time and the historical wind power data, inputting the preprocessed data into the trained wind power prediction network model, and outputting a result as a prediction result of the wind power in a future specified time interval.
2. The wind power prediction method based on the deep learning fusion model as claimed in claim 1, wherein the step of data preprocessing comprises:
and (3) data format analysis: analyzing the data formats of the wind power real-time monitoring data and/or historical wind power data in different data formats taken from the SCADA system, and converting the data formats into a unified format;
analyzing data correlation to eliminate wind power real-time monitoring data and historical wind power data with the weight lower than a set threshold;
normalization processing, namely normalizing the wind power real-time monitoring data and the historical wind power data according to a formula (1);
Figure FDA0003378407170000011
where w' is a normalized value, w represents the true value of the sample, wminAnd wmaxRepresenting the minimum and maximum values selected.
3. The wind power prediction method based on the deep learning fusion model of claim 2, wherein the wind power prediction network model comprises a feature extraction module, a context information extraction module, a key information prediction module, a feature fusion module and a result prediction module which are connected in sequence; wherein the content of the first and second substances,
the characteristic extraction module is a characteristic extraction neural network and is used for extracting characteristics of the wind power real-time monitoring data and the historical wind power data to obtain corresponding text space-time characteristics;
the context information extraction module is used for acquiring the sequence relation of the wind power real-time monitoring data and the historical wind power data on a time sequence to obtain the context information of the wind power real-time monitoring data and the historical wind power data;
the key information prediction module is used for acquiring interactive characteristics in the features of the mined wind power real-time monitoring data and the historical wind power data to form context features of the wind power real-time monitoring data and the historical wind power data with key prediction information;
the characteristic fusion module is used for fusing and splicing the context characteristics of the wind power real-time monitoring data and the historical wind power data to obtain characteristic fusion information;
and the result prediction module is used for calculating a prediction result according to the feature fusion information to complete wind power prediction.
4. The wind power prediction method based on the deep learning fusion model of claim 3, characterized in that the feature extraction neural network is a convolutional neural network model (CNN network); the convolutional neural network model CNN network comprises 1 convolutional layer and 1 pooling layer, and high-frequency space-time characteristics are obtained by adopting a maximum pooling method.
5. The wind power prediction method based on the deep learning fusion model as claimed in claim 4, wherein the context information extraction module adopts a BilSTM network model, inputs the high-frequency spatiotemporal features into the BilSTM network model, outputs the context relationship of data at different moments, and performs redundant information filtering by using a forgetting gate of the BilSTM network model to improve text feature characterization and fitting capability.
6. The wind power prediction method based on the deep learning fusion model as claimed in claim 3, wherein the key information prediction module obtains different weights inside the features for the real-time wind power monitoring data and the historical wind power data by using a self-attention and interactive attention mechanism in bidirectional attention, and exploits interactive characteristics inside the features of the two data, thereby finally forming the context features with the key prediction information.
7. The wind power prediction method based on the deep learning fusion model as claimed in claim 4, wherein the step of training the built wind power prediction network model through the training set comprises:
inputting the preprocessed training set data into a feature extraction neural network of a feature extraction module, and performing feature extraction through a convolutional neural network model (CNN) network;
obtaining a sequence relation of a past moment and a future moment by using a BilSTM network model so as to obtain context information;
respectively acquiring context characteristics with key prediction information from real-time wind power monitoring data and historical wind power data by utilizing a self-attention and interactive attention mechanism in bidirectional attention, mining interactive characteristics in the characteristics of the two kinds of data, and respectively forming interactive characteristics of the two kinds of data containing the context information;
merging the interactive features containing the context information to obtain fused features, wherein the fused features contain the context information and the interactive features, and fully reflect the contribution degree of real-time data and historical data to wind power prediction;
and calculating a prediction result by using the full connection layer, comparing the prediction result with a marked detection result, and finishing network training by continuously adjusting network functions and parameters until the prediction result is consistent with an actual power result.
8. The wind power prediction method based on the deep learning fusion model as claimed in claim 4, characterized by further comprising a step of displaying a result after the step of outputting the prediction result of the wind power; wherein, the result display mode at least comprises: the method comprises the following steps of character display, voice broadcast, terminal outbound, mail and short message transmission, intelligent sound box and voice awakening.
9. The utility model provides a wind-powered electricity generation power prediction unit based on deep learning fuses model which characterized in that includes:
the data processing module is used for acquiring wind power real-time monitoring data in a specified time interval, acquiring historical wind power data at the same time, preprocessing the data, and taking the preprocessed wind power real-time monitoring data and the historical wind power data as a training set;
the network construction module is used for constructing a wind power prediction network model and training the constructed wind power prediction network model through the training set; the wind power prediction network model comprises a feature extraction module, a context information extraction module, a key information prediction module, a feature fusion module and a result prediction module which are connected in sequence;
and the power prediction module is used for preprocessing the real-time monitoring data of the wind power generated in real time and the historical wind power data, inputting the preprocessed data into the trained wind power prediction network model, and outputting a result as a prediction result of the wind power in a future specified time interval.
10. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the method of any one of claims 1-8 when executing the computer program.
11. A non-transitory computer readable storage medium having stored thereon a computer program, wherein the computer program, when executed by a processor, implements the method of any one of claims 1-8.
CN202111424160.5A 2021-11-26 2021-11-26 Wind power prediction method and device based on deep learning fusion model Pending CN114330495A (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
CN202111424160.5A CN114330495A (en) 2021-11-26 2021-11-26 Wind power prediction method and device based on deep learning fusion model
PCT/CN2022/099615 WO2023093010A1 (en) 2021-11-26 2022-06-17 Wind power prediction method and device based on deep learning fusion model

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202111424160.5A CN114330495A (en) 2021-11-26 2021-11-26 Wind power prediction method and device based on deep learning fusion model

Publications (1)

Publication Number Publication Date
CN114330495A true CN114330495A (en) 2022-04-12

Family

ID=81047455

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202111424160.5A Pending CN114330495A (en) 2021-11-26 2021-11-26 Wind power prediction method and device based on deep learning fusion model

Country Status (2)

Country Link
CN (1) CN114330495A (en)
WO (1) WO2023093010A1 (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023093010A1 (en) * 2021-11-26 2023-06-01 中国华能集团清洁能源技术研究院有限公司 Wind power prediction method and device based on deep learning fusion model

Families Citing this family (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN116826727B (en) * 2023-06-28 2024-02-23 河海大学 Ultra-short-term wind power prediction method and prediction system based on time sequence representation and multistage attention
CN116581756B (en) * 2023-07-13 2023-12-12 华北电力大学 Wind power prediction method, model training method, device, equipment and medium
CN117349650B (en) * 2023-09-20 2024-04-12 同济大学 Method for extracting foundation pit structural data multi-element space-time fusion and evolution features
CN117498555A (en) * 2023-11-07 2024-02-02 广东格林赛福能源科技有限公司 Cloud-edge fusion-based intelligent operation and maintenance system for energy storage power station
CN117557304B (en) * 2024-01-11 2024-03-29 国网浙江省电力有限公司 Electric quantity and electricity price level fusion prediction method based on modal decomposition and neural network

Family Cites Families (11)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP6086875B2 (en) * 2014-02-06 2017-03-01 三菱重工業株式会社 Power generation amount prediction device and power generation amount prediction method
EP3464895B1 (en) * 2016-05-23 2021-10-13 General Electric Company System and method for forecasting power output of a wind farm
CN110059878B (en) * 2019-04-15 2021-04-02 中国计量大学 Photovoltaic power generation power prediction model based on CNN LSTM and construction method thereof
CN110443725A (en) * 2019-08-14 2019-11-12 国网甘肃省电力公司信息通信公司 Wind power prediction model based on CNN+LSTM
KR20210023388A (en) * 2019-08-23 2021-03-04 주식회사 화성 Photo-voltiac prediction system based on machine learning
CN113642225A (en) * 2021-05-24 2021-11-12 国网新疆电力有限公司经济技术研究院 CNN-LSTM short-term wind power prediction method based on attention mechanism
CN113205226B (en) * 2021-05-28 2022-10-14 河北工业大学 Photovoltaic power prediction method combining attention mechanism and error correction
CN114330495A (en) * 2021-11-26 2022-04-12 中国华能集团清洁能源技术研究院有限公司 Wind power prediction method and device based on deep learning fusion model
CN114330097A (en) * 2021-11-26 2022-04-12 中国华能集团清洁能源技术研究院有限公司 Heterogeneous data and deep learning wind power cluster power prediction method and device
CN114358371A (en) * 2021-11-26 2022-04-15 华能大理风力发电有限公司洱源分公司 Photovoltaic short-term power prediction method and device based on deep learning
CN114330493A (en) * 2021-11-26 2022-04-12 中国华能集团清洁能源技术研究院有限公司 CNN + BiLSTM + Attention wind power ultra-short term power prediction method and system

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
WO2023093010A1 (en) * 2021-11-26 2023-06-01 中国华能集团清洁能源技术研究院有限公司 Wind power prediction method and device based on deep learning fusion model

Also Published As

Publication number Publication date
WO2023093010A1 (en) 2023-06-01

Similar Documents

Publication Publication Date Title
CN114330495A (en) Wind power prediction method and device based on deep learning fusion model
CN106650780B (en) Data processing method and device, classifier training method and system
US20230123117A1 (en) Method and Apparatus for Inspecting Wind Turbine Blade, And Device And Storage Medium Thereof
CN114463594A (en) Multi-mode deep learning power generation equipment abnormity integrated identification method and equipment
WO2023093774A1 (en) Deep learning-based wind power cluster power prediction method
CN114358371A (en) Photovoltaic short-term power prediction method and device based on deep learning
CN113392253B (en) Visual question-answering model training and visual question-answering method, device, equipment and medium
CN112699998B (en) Time series prediction method and device, electronic equipment and readable storage medium
CN111831430A (en) Electrical equipment defect identification system based on edge calculation
WO2023088315A1 (en) Power generation device abnormality detection method and system based on deep learning
CN111079861A (en) Power distribution network voltage abnormity diagnosis method based on image rapid processing technology
CN113822418A (en) Wind power plant power prediction method, system, device and storage medium
CN115859099A (en) Sample generation method and device, electronic equipment and storage medium
CN114610901A (en) Power grid operation data fusion method and device and storage medium
CN117056865B (en) Method and device for diagnosing operation faults of machine pump equipment based on feature fusion
CN114330493A (en) CNN + BiLSTM + Attention wind power ultra-short term power prediction method and system
CN116910633B (en) Power grid fault prediction method based on multi-modal knowledge mixed reasoning
CN113076985A (en) Power consumer load identification method and device and computer readable medium
CN117079005A (en) Optical cable fault monitoring method, system, device and readable storage medium
CN116164822A (en) Knowledge graph-based flowmeter fault diagnosis method, device and medium
CN116523681A (en) Load decomposition method and device for electric automobile, electronic equipment and storage medium
CN115563507A (en) Generation method, device and equipment for renewable energy power generation scene
CN115880472A (en) Intelligent diagnosis and analysis system for electric power infrared image data
CN115828091A (en) Non-invasive load identification method and system based on end-cloud cooperation
CN114330494A (en) BiLSTM and attention fused power generation equipment abnormity prediction method and system

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