CN115983486A - Wind power output prediction method and device, electronic equipment and storage medium - Google Patents
Wind power output prediction method and device, electronic equipment and storage medium Download PDFInfo
- Publication number
- CN115983486A CN115983486A CN202310028559.4A CN202310028559A CN115983486A CN 115983486 A CN115983486 A CN 115983486A CN 202310028559 A CN202310028559 A CN 202310028559A CN 115983486 A CN115983486 A CN 115983486A
- Authority
- CN
- China
- Prior art keywords
- wind power
- power output
- target
- sample
- output prediction
- 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
- 238000000034 method Methods 0.000 title claims abstract description 49
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 36
- 238000005457 optimization Methods 0.000 claims abstract description 27
- 230000006870 function Effects 0.000 claims description 34
- 238000004590 computer program Methods 0.000 claims description 16
- 210000002569 neuron Anatomy 0.000 claims description 9
- 230000004913 activation Effects 0.000 claims description 5
- 238000010276 construction Methods 0.000 claims description 3
- 238000012935 Averaging Methods 0.000 claims 1
- 238000012549 training Methods 0.000 abstract description 14
- 238000013528 artificial neural network Methods 0.000 abstract description 6
- 238000013527 convolutional neural network Methods 0.000 description 38
- 238000010586 diagram Methods 0.000 description 10
- 238000004891 communication Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 5
- 230000003287 optical effect Effects 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 101001095088 Homo sapiens Melanoma antigen preferentially expressed in tumors Proteins 0.000 description 2
- 102100037020 Melanoma antigen preferentially expressed in tumors Human genes 0.000 description 2
- 229910052731 fluorine Inorganic materials 0.000 description 2
- 125000001153 fluoro group Chemical group F* 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000035772 mutation Effects 0.000 description 2
- 238000005070 sampling Methods 0.000 description 2
- 238000003491 array Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001413 cellular effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 239000004973 liquid crystal related substance Substances 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000007726 management method Methods 0.000 description 1
- 230000001537 neural effect Effects 0.000 description 1
- 239000013307 optical fiber Substances 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 230000001953 sensory effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000002123 temporal effect Effects 0.000 description 1
- 230000000007 visual effect Effects 0.000 description 1
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a wind power output prediction method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring historical data of target wind power output of a target wind power plant in a preset historical time period; inputting the target wind power output historical data into a target wind power output prediction model to obtain target wind power output prediction data; the target wind power output prediction model is obtained by performing parameter optimization on the wind power output prediction model to be optimized based on a sample wind power output prediction result and a differential evolution algorithm taking a symmetric average absolute percentage error as a target function; and predicting the historical data of the sample wind power output based on the wind power output prediction model to be optimized according to the prediction result of the sample wind power output. The network parameters of the wind power output prediction model to be optimized are adaptively adjusted by adopting a differential evolution algorithm, the network structure is optimized, the advantages of a neural network are fully exerted, and the time and energy consumed in parameter adjustment in the conventional network training are reduced.
Description
Technical Field
The invention relates to the technical field of power prediction, in particular to a wind power output prediction method and device, electronic equipment and a storage medium.
Background
With the global shortage of energy and the increasing severity of environmental problems, wind energy has received much attention as a clean, pollution-free, widely distributed, renewable energy source that is easy to develop and utilize. The accurate and reliable short-term wind power prediction can not only help the wind power plant to carry out work planning, but also reduce the influence of wind power access on a power grid, and is one of the keys in wind energy utilization. The existing wind power prediction technology needs manual adjustment of neural network parameters, consumes a great deal of time and energy, and has poor prediction effect on wind power output.
Disclosure of Invention
The invention provides a wind power output prediction method, a wind power output prediction device, electronic equipment and a storage medium, aims to solve the problem of difficulty in parameter adjustment, adaptively adjusts parameters of a wind power output prediction network according to a prediction result by utilizing an improved differential evolution algorithm, optimizes a network structure, fully exerts the advantages of a neural network, reduces time and energy consumed in parameter adjustment, and improves the prediction effect on wind power output.
According to an aspect of the present invention, a wind power output prediction method is provided, including:
acquiring historical data of target wind power output of a target wind power plant in a preset historical time period;
inputting the target wind power output historical data into a target wind power output prediction model to obtain target wind power output prediction data of the target wind power plant output by the target wind power output prediction model;
the target wind power output prediction model is obtained by performing parameter optimization on a wind power output prediction model to be optimized based on a sample wind power output prediction result and a differential evolution algorithm with a symmetric average absolute percentage error as a target function; and predicting the sample wind power output prediction result on the basis of the wind power output prediction model to be optimized on the sample wind power output historical data.
Further, before the target wind power output historical data is input into the target wind power output prediction model, the method includes:
collecting sample wind power output historical data of a target wind power plant;
constructing a wind power output prediction model to be optimized, wherein the wind power output prediction model to be optimized comprises a CNN (convolutional neural network) and an LSTM (least squares metric) prediction network;
inputting the historical data of the sample wind power output into the wind power output prediction model to be optimized to obtain a prediction result of the sample wind power output;
and performing parameter optimization on the CNN convolutional network and the LSTM prediction network based on the sample wind power output prediction result and a differential evolution algorithm taking a symmetric average absolute percentage error as a target function.
Further, the performing parameter optimization on the CNN convolutional network and the LSTM prediction network based on the sample wind power output prediction result and a differential evolution algorithm with a symmetric average absolute percentage error as a target function includes:
adjusting a first parameter of the CNN network based on the sample wind power output prediction result;
adjusting a second parameter of the LSTM prediction network based on the sample wind power output prediction result;
determining a symmetric average absolute percentage error of the sample wind power output prediction result and the sample wind power output historical data;
and determining the optimal parameters of the CNN network and the LSTM prediction network in the wind power output prediction model to be optimized according to a differential evolution algorithm taking the symmetric average absolute percentage error as a target function.
Further, the symmetric mean absolute percentage error includes:
wherein: SMAPE is the mean absolute percent error of symmetry,
is sample wind power output prediction data, y i The data is sample wind power output historical data, and n is the data volume of the sample wind power output historical data.
Further, the first parameter includes: learning rate, batch sample number and maximum iteration number in the CNN network;
the second parameter includes: LSTM predicts the number of hidden layer neurons, the drop rate, and the time lag order in the network.
Further, the CNN network is represented as:
O t ＝σ(W*x t +b)；
wherein W represents a convolution kernel; x is a radical of a fluorine atom t Representing a time sequence formed by second wind power output historical data of the target wind power plant; * Representing a discrete convolution operator; b represents a bias parameter; σ represents an activation function; o is t And representing feature data output after convolution operation.
According to another aspect of the present invention, there is provided a wind power output prediction apparatus, including:
the target data acquisition module is used for acquiring target wind power output historical data of a target wind power plant in a preset historical time period;
the target data prediction module is used for inputting the target wind power output historical data into a target wind power output prediction model to obtain target wind power output prediction data of the target wind power plant output by the target wind power output prediction model;
the target wind power output prediction model is obtained by performing parameter optimization on a wind power output prediction model to be optimized based on a sample wind power output prediction result and a differential evolution algorithm taking a symmetric average absolute percentage error as a target function; and predicting the historical data of the sample wind power output based on the wind power output prediction model to be optimized according to the prediction result of the sample wind power output.
Further, the apparatus further comprises:
the sample data acquisition module is used for acquiring sample wind power output historical data of a target wind power plant before inputting the target wind power output historical data into the target wind power output prediction model;
the wind power output prediction model to be optimized is constructed by the prediction model construction module and comprises a CNN (convolutional network) and an LSTM (least Square TM) prediction network;
the sample data prediction module is used for inputting the historical wind power output data of the sample into the wind power output prediction model to be optimized to obtain a prediction result of the wind power output of the sample;
and the parameter optimization module is used for optimizing parameters of the CNN convolutional network and the LSTM prediction network based on the sample wind power output prediction result and a differential evolution algorithm taking a symmetric average absolute percentage error as a target function.
According to another aspect of the present invention, there is provided an electronic apparatus including:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor, the computer program being executable by the at least one processor to enable the at least one processor to perform the wind power output prediction method according to any of the embodiments of the present invention.
According to another aspect of the present invention, a computer-readable storage medium is provided, which stores computer instructions for causing a processor to implement the wind power output prediction method according to any one of the embodiments of the present invention when executed.
According to the technical scheme of the embodiment of the invention, the historical data of the output of the target wind power in the preset historical time period of the target wind power plant is acquired; inputting the target wind power output historical data into a target wind power output prediction model to obtain target wind power output prediction data of a target wind power plant output by the target wind power output prediction model; the target wind power output prediction model is obtained by performing parameter optimization on the wind power output prediction model to be optimized based on a sample wind power output prediction result and a differential evolution algorithm taking a symmetric average absolute percentage error as a target function; and predicting the sample wind power output prediction result based on the wind power output prediction model to be optimized to obtain the sample wind power output historical data. The network parameters of the wind power output prediction model to be optimized are adaptively adjusted by adopting a differential evolution algorithm, the network structure is optimized, the advantages of a neural network are fully exerted, the time and energy consumed in parameter adjustment in the conventional network training are reduced, the adjustment of the network parameters is more accurate, and the prediction effect on the wind power output is improved.
It should be understood that the statements in this section do not necessarily identify key or critical features of the embodiments of the present invention, nor do they necessarily limit the scope of the invention. Other features of the present invention will become apparent from the following description.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required to be used in the description of the embodiments are briefly introduced below, and it is obvious that the drawings in the description below are only some embodiments of the present invention, and it is obvious for those skilled in the art that other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a flowchart of a wind power output prediction method according to an embodiment of the present invention;
fig. 2A is a flowchart of a wind power output prediction method according to a second embodiment of the present invention;
fig. 2B is a schematic diagram illustrating parameter adjustment performed on a CNN network in the wind power output prediction method according to the second embodiment of the present invention;
fig. 2C is a schematic diagram illustrating parameter adjustment performed on an LSTM network in the wind power output prediction method according to the second embodiment of the present invention;
fig. 2D is a schematic diagram illustrating parameter adjustment performed on a wind power output prediction model to be optimized in the wind power output prediction method according to the second embodiment of the present invention;
fig. 2E is a schematic diagram of parameter optimization performed on a CNN network and an LSTM prediction network in the wind power output prediction method according to the second embodiment of the present invention.
Fig. 3 is a schematic structural diagram of a wind power output prediction apparatus provided by a third embodiment of the present invention;
fig. 4 is a schematic structural diagram of an electronic device implementing the wind power output prediction method according to the embodiment of the present invention.
Detailed Description
In order to make the technical solutions of the present invention better understood, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
It should be noted that the terms "first," "second," and the like in the description and claims of the present invention and in the drawings described above are used for distinguishing between similar elements and not necessarily for describing a particular sequential or chronological order. It is to be understood that the data so used is interchangeable under appropriate circumstances such that the embodiments of the invention described herein are capable of operation in sequences other than those illustrated or described herein. Furthermore, the terms "comprises," "comprising," and "having," and any variations thereof, are intended to cover a non-exclusive inclusion, such that a process, method, system, article, or apparatus that comprises a list of steps or elements is not necessarily limited to those steps or elements expressly listed, but may include other steps or elements not expressly listed or inherent to such process, method, article, or apparatus.
Example one
Fig. 1 is a flowchart of a wind power output prediction method according to an embodiment of the present invention, where the embodiment is applicable to a wind power output prediction situation, the method may be executed by a wind power output prediction device, the wind power output prediction device may be implemented in a hardware and/or software manner, and the wind power output prediction device may be configured in an electronic device. As shown in fig. 1, the method includes:
s110, collecting historical data of target wind power output of a target wind power plant in a preset historical time period.
The target wind power plant can be understood as a wind power plant needing wind power output prediction, the whole wind power output of all wind motors in the wind power plant can be predicted, and the wind power output prediction can also be performed on one or more specified wind motors in the wind power plant. The target wind power output historical data is historical wind power output data collected from a target wind power place and is used for predicting wind power output data of a target wind power plant, namely the target wind power output historical data is used as a prediction data set in the embodiment.
Specifically, the method for collecting the historical data of the target wind power output may be as follows: and acquiring the wind power output data of the wind motors of the target wind power plant in a preset historical time period at fixed data sampling intervals to obtain the target wind power output historical data.
For example, as shown in table 1, output data of a certain fan of a target wind farm in 15 months is collected at data sampling intervals of 10min and is used as target wind power output historical data.
TABLE 1
S120, inputting the target wind power output historical data into a target wind power output prediction model to obtain target wind power output prediction data of a target wind power plant output by the target wind power output prediction model; the target wind power output prediction model is obtained by performing parameter optimization on a wind power output prediction model to be optimized based on a sample wind power output prediction result and a differential evolution algorithm with a symmetric average absolute percentage error as a target function; and predicting the sample wind power output prediction result based on the wind power output prediction model to be optimized to obtain the sample wind power output historical data.
In this embodiment, the wind power output prediction model to be optimized refers to a wind power output prediction network which needs parameter optimization; the sample wind power output prediction result refers to a result predicted by a wind power output prediction model to be optimized on wind power output historical data serving as a training sample. The target wind power output prediction model is a wind power output prediction network obtained after the wind power output prediction model to be optimized is subjected to parameter optimization; the target wind power output prediction data is wind power output data obtained by prediction based on the target wind power output prediction model.
The Symmetric Mean Absolute Percentage Error (SMAPE) is used for correcting the Mean Absolute Percentage Error MAPE, and a differential evolution algorithm with the Symmetric Mean Absolute Percentage Error as an objective function can better avoid the problem that the calculation result is larger when the true value is smaller (MAPE).
Specifically, according to a sample wind power output prediction result obtained by predicting wind power output historical data serving as a training sample by the wind power output prediction model to be optimized and a differential evolution algorithm with a symmetric average absolute percentage error as a target function, parameter optimization is carried out on the wind power output prediction model to be optimized to obtain a target wind power output prediction model. And inputting the target wind power output historical data into the target wind power output prediction model to obtain the target wind power output prediction data of the target wind power plant output by the target wind power output prediction model, thereby realizing the prediction of the wind power output data of the target wind power plant.
According to the technical scheme of the embodiment of the invention, the historical data of the output of the target wind power in the preset historical time period of the target wind power plant is collected; inputting the target wind power output historical data into a target wind power output prediction model to obtain target wind power output prediction data of a target wind power plant output by the target wind power output prediction model; the target wind power output prediction model is obtained by performing parameter optimization on the wind power output prediction model to be optimized based on a sample wind power output prediction result and a differential evolution algorithm with a symmetric average absolute percentage error as a target function; and predicting the sample wind power output prediction result based on the wind power output prediction model to be optimized to obtain the sample wind power output historical data. The network parameters of the wind power output prediction model to be optimized are adaptively adjusted by adopting a differential evolution algorithm, the network structure is optimized, the advantages of a neural network are fully exerted, the time and energy consumed in parameter adjustment in the conventional network training are reduced, the adjustment of the network parameters is more accurate, and the prediction effect on the wind power output is improved.
Example two
Fig. 2A is a flowchart of a wind power output prediction method according to a second embodiment of the present invention, and this embodiment further refines the step of "performing parameter optimization on a to-be-optimized wind power output prediction model based on a sample wind power output prediction result and a differential evolution algorithm" in the above-mentioned embodiment. As shown in fig. 2A, the method includes:
s210, collecting sample wind power output historical data of the target wind power plant.
Specifically, sample wind power output historical data of a wind motor of a target wind power plant in a historical time period is collected at fixed time intervals and used as a training sample for iterative training and optimization of a wind power output prediction model to be optimized.
S220, constructing a wind power output prediction model to be optimized, wherein the wind power output prediction model to be optimized comprises a CNN (convolutional network) and an LSTM (least Square TM) prediction network.
The wind power output prediction model to be optimized can be an untrained wind power output prediction network or a pre-trained wind power output prediction network.
Specifically, the constructed wind power output prediction model to be optimized comprises a CNN convolutional network and an LSTM prediction network. And the CNN convolutional network is used for carrying out convolution operation on the historical wind power output data of the sample to extract high-dimensional data characteristics. The LSTM prediction network is used for temporal prediction based on high dimensional data features.
Optionally, the CNN network is represented by O t ＝σ(W*x t +b)；
Wherein W represents a convolution kernel; x is a radical of a fluorine atom t Representing a time sequence formed by second wind power output historical data of the target wind power plant; * Representing a discrete convolution operator; b represents a bias parameter; σ represents an activation function; o is t And representing feature data output after convolution operation.
Optionally, the LSTM prediction network includes three gate control units, which are a forgetting gate, a memory gate, and an output gate, respectively;
a memory gate: i.e. i t ＝σ(W i ·h t-1 +W i ·x t +b i )，k t ＝tanh(W k ·h t-1 +W k ·x t +b k )；
Forget the door: f. of t ＝σ(W f ·h t-1 +W f ·O t +b f )；
An output gate: c. C t ＝f t *c t-1 +i t *k t ；
Wherein h is t-1 Indicating information transferred at time t-1, O t Representing the input vector, W, of the LSTM network resulting from the convolution at time t f 、W i And W k Represents a weight value, b i 、b k And b f Representing an offset value, f t Is the vector measured for the past memory, x, obtained by the forgetting gate at time t t Representing an input vector of the LSTM prediction network at the time t; c. C t Representing the output value of the output gate at time t, c t-1 Represents the output value of the output gate at time t-1 and sigma represents the activation function.
And S230, inputting the historical data of the sample wind power output into a wind power output prediction model to be optimized to obtain a prediction result of the sample wind power output.
The sample wind power output prediction result is a prediction result obtained by prediction according to sample wind power output historical data.
Specifically, the historical wind power output data of the sample is used as a training sample and input into a wind power output prediction model to be optimized, the characteristic extraction is carried out through a CNN convolution network of the wind power output prediction model to be optimized, and the prediction is carried out through an LSTM prediction network to obtain a wind power output prediction result of the sample.
S240, based on the sample wind power output prediction result and a differential evolution algorithm with the symmetric average absolute percentage error as a target function, parameter optimization is carried out on the CNN convolutional network and the LSTM prediction network.
Specifically, according to dynamic feedback of a sample wind power output prediction result corresponding to sample wind power output historical data output by a wind power output prediction model to be optimized, parameter adjustment is carried out on a CNN convolution network and an LSTM prediction network of the wind power output prediction model to be optimized, parameter optimization is carried out on the CNN convolution network and the LSTM prediction network of the wind power output prediction model to be optimized according to a differential evolution algorithm with a symmetric average absolute percentage error as a target function, and network optimal parameters enabling the symmetric average absolute percentage error to be minimum are determined.
Optionally, S240, performing parameter optimization on the CNN convolutional network and the LSTM prediction network based on the sample wind power output prediction result and a differential evolution algorithm with a symmetric average absolute percentage error as a target function, including:
s241, adjusting the first parameter of the CNN network based on the sample wind power output prediction result.
Wherein the first parameter of the CNN network may include: learning rate, batch sample number, and maximum number of iterations in the CNN network.
The learning rate represents the amplitude of each parameter update and determines whether the target function can be converged to a local minimum value or not and the speed of converging to the local minimum value; the batch processing sample number represents the number of samples selected in one training, and has influence on the training speed and the use condition of a memory; the number of iterations represents the number of times of training using the data set, and the appropriate number of iterations needs to be selected to strike a balance between training time and model accuracy.
Specifically, as shown in fig. 2B, the sample wind power output prediction result is subjected to parameter adjustment on the learning rate, the number of batch processing samples, and the maximum iteration number in the CNN network through dynamic feedback.
And S242, adjusting a second parameter of the LSTM prediction network based on the sample wind power output prediction result.
Wherein the second parameter of the LSTM prediction network comprises: LSTM predicts the number of hidden layer neurons, the drop rate, and the time lag order in the network.
The number of neurons in the hidden layer has an influence on the fitting capability of the LSTM prediction network, so that too few neurons are used in the hidden layer, so that under-fitting is caused, and excessive neurons can cause over-fitting; the discarding rate is the probability that the neural unit is discarded randomly in the LSTM prediction network training, and the reasonable discarding rate can reduce overfitting of the network; the time lag order refers to how long a parameter is predicted for each quantity to be predicted, and is related to the accuracy of the prediction.
Specifically, as shown in fig. 2C, according to the sample wind power output prediction result and the high-dimensional data characteristics output by the CNN, the number of neurons in the hidden layer, the discarding rate, and the time lag order in the LSTM prediction network are subjected to parameter adjustment through dynamic feedback.
And S243, determining the symmetric average absolute percentage error of the sample wind power output prediction result and the sample wind power output historical data.
Optionally, the symmetric mean absolute percentage error includes:
wherein: SMAPE is the symmetric mean absolute percent error,
is sample wind power output prediction data, y i The data is sample wind power output historical data, and n is the data volume of the sample wind power output historical data.
And S244, determining the optimal parameters of the CNN network and the LSTM prediction network in the wind power output prediction model to be optimized according to a differential evolution algorithm taking the symmetric average absolute percentage error as a target function.
Specifically, parameters needing to be adjusted in the parameters of the wind power output prediction network are determined, and the data size, the mutation operator, the maximum evolution frequency and the termination condition of the sample wind power output historical data in the differential evolution algorithm are determined. As shown in fig. 2D, calculating an objective function value that can be calculated from the sample wind power output historical data, continuously performing mutation operation and crossover operation, and optimizing a first parameter of the CNN network and a second parameter of the LSTM prediction network by using a differential evolution algorithm that takes the symmetric mean absolute percentage error SMAPE as an objective function, so as to find out a network optimal parameter that can minimize the symmetric mean absolute percentage error, thereby obtaining a high-precision wind power output prediction network.
Illustratively, fig. 2E is a schematic diagram of parameter optimization for CNN networks and LSTM prediction networks. A first parameter of the CNN network is processed by a differential evolution algorithm: learning rate, batch sample number and maximum iteration number, and a second parameter of the LSTM prediction network: optimizing the number of neurons in the hidden layer, the discarding rate and the time lag order, finding out a network optimal parameter S250 capable of minimizing the symmetric average absolute percentage error, and collecting target wind power output historical data of a target wind power plant in a preset historical time period.
And S260, inputting the target wind power output historical data into a target wind power output prediction model to obtain target wind power output prediction data of a target wind power plant output by the target wind power output prediction model.
According to the technical scheme of the embodiment of the invention, the historical data of the wind power output of the sample of the target wind power plant is acquired; constructing a wind power output prediction model to be optimized, wherein the wind power output prediction model to be optimized comprises a CNN (convolutional network) and an LSTM (least Square TM) prediction network; inputting the historical wind power output data of the sample into a wind power output prediction model to be optimized to obtain a wind power output prediction result of the sample; performing parameter optimization on the CNN convolutional network and the LSTM prediction network based on a sample wind power output prediction result and a differential evolution algorithm with a symmetric average absolute percentage error as a target function; acquiring historical data of target wind power output of a target wind power plant in a preset historical time period; and inputting the target wind power output historical data into a target wind power output prediction model to obtain target wind power output prediction data of a target wind power plant output by the target wind power output prediction model. The network parameters of the wind power output prediction model to be optimized are adaptively adjusted by adopting a differential evolution algorithm taking the symmetric average absolute percentage error as a target function, the network structure is optimized, the advantages of a neural network are fully exerted, the time and energy consumed in parameter adjustment in the conventional network training are reduced, the adjustment of the network parameters is more accurate, and the prediction effect on the wind power output is improved.
EXAMPLE III
Fig. 3 is a schematic structural diagram of a wind power output prediction apparatus provided in the third embodiment of the present invention.
As shown in fig. 3, the apparatus includes:
the target data acquisition module 310 is used for acquiring target wind power output historical data of a target wind power plant in a preset historical time period;
the target data prediction module 320 is used for inputting the target wind power output historical data into a target wind power output prediction model to obtain target wind power output prediction data of the target wind power plant output by the target wind power output prediction model;
the target wind power output prediction model is obtained by performing parameter optimization on a to-be-optimized wind power output prediction model based on a sample wind power output prediction result and a differential evolution algorithm; and predicting the sample wind power output prediction result on the basis of the wind power output prediction model to be optimized on the sample wind power output historical data.
Optionally, the method further includes:
the sample data acquisition module is used for acquiring sample wind power output historical data of a target wind power plant before inputting the target wind power output historical data into the target wind power output prediction model;
the wind power output prediction model to be optimized is constructed by the prediction model construction module and comprises a CNN (convolutional network) and an LSTM (least Square TM) prediction network;
the sample data prediction module is used for inputting the historical wind power output data of the sample into the wind power output prediction model to be optimized to obtain a prediction result of the wind power output of the sample;
and the parameter optimization module is used for optimizing parameters of the CNN convolutional network and the LSTM prediction network based on the sample wind power output prediction result and a differential evolution algorithm taking a symmetric average absolute percentage error as a target function.
Optionally, the parameter optimization module is specifically configured to:
adjusting a first parameter of the CNN network based on the sample wind power output prediction result;
adjusting a second parameter of the LSTM prediction network based on the sample wind power output prediction result;
determining a symmetric average absolute percentage error of the sample wind power output prediction result and the sample wind power output historical data;
and determining the optimal parameters of the CNN network and the LSTM prediction network in the wind power output prediction model to be optimized according to a differential evolution algorithm taking the symmetric average absolute percentage error as a target function.
Optionally, the symmetric mean absolute percentage error includes:
wherein: SMAPE is the mean absolute percent error of symmetry,
is sample wind power output prediction data, y i The data is sample wind power output historical data, and n is the data volume of the sample wind power output historical data.
Optionally, the first parameter includes: learning rate, batch sample number and maximum iteration number in the CNN network;
the second parameter includes: LSTM predicts the number of hidden layer neurons, the drop rate, and the time lag order in the network.
Optionally, the CNN network is represented as:
O t ＝σ(W*x t +b)；
wherein W represents a convolution kernel; x is the number of t Representing a time sequence formed by second wind power output historical data of the target wind power plant; * Representing a discrete convolution operator; b represents a bias parameter; σ represents an activation function; o is t And representing feature data output after convolution operation.
The wind power output prediction device provided by the embodiment of the invention can execute the wind power output prediction method provided by any embodiment of the invention, and has the corresponding functional modules and beneficial effects of the execution method.
Example four
FIG. 4 shows a schematic block diagram of an electronic device 10 that may be used to implement an embodiment of the invention. Electronic devices are intended to represent various forms of digital computers, such as laptops, desktops, workstations, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device may also represent various forms of mobile devices, such as personal digital assistants, cellular phones, smart phones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions, are meant to be exemplary only, and are not meant to limit implementations of the inventions described and/or claimed herein.
As shown in fig. 4, the electronic device 10 includes at least one processor 11, and a memory communicatively connected to the at least one processor 11, such as a Read Only Memory (ROM) 12, a Random Access Memory (RAM) 13, and the like, wherein the memory stores a computer program executable by the at least one processor, and the processor 11 can perform various suitable actions and processes according to the computer program stored in the Read Only Memory (ROM) 12 or the computer program loaded from a storage unit 18 into the Random Access Memory (RAM) 13. In the RAM 13, various programs and data necessary for the operation of the electronic apparatus 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input/output (I/O) interface 15 is also connected to the bus 14.
A number of components in the electronic device 10 are connected to the I/O interface 15, including: an input unit 16 such as a keyboard, a mouse, or the like; an output unit 17 such as various types of displays, speakers, and the like; a storage unit 18 such as a magnetic disk, an optical disk, or the like; and a communication unit 19 such as a network card, modem, wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information/data with other devices via a computer network such as the internet and/or various telecommunication networks.
The processor 11 may be a variety of general and/or special purpose processing components having processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a Central Processing Unit (CPU), a Graphics Processing Unit (GPU), various specialized Artificial Intelligence (AI) computing chips, various processors running machine learning model algorithms, a Digital Signal Processor (DSP), and any suitable processor, controller, microcontroller, or the like. Processor 11 performs the various methods and processes described above, such as the wind power output prediction method.
In some embodiments, the wind power output prediction method may be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and/or installed onto the electronic device 10 via the ROM 12 and/or the communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the wind power output prediction method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the wind power output prediction method by any other suitable means (e.g., by means of firmware).
Various implementations of the systems and techniques described here above may be implemented in digital electronic circuitry, integrated circuitry, field Programmable Gate Arrays (FPGAs), application Specific Integrated Circuits (ASICs), application Specific Standard Products (ASSPs), system on a chip (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and/or combinations thereof. These various embodiments may include: implemented in one or more computer programs that are executable and/or interpretable on a programmable system including at least one programmable processor, which may be special or general purpose, receiving data and instructions from, and transmitting data and instructions to, a storage system, at least one input device, and at least one output device.
A computer program for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions/acts specified in the flowchart and/or block diagram block or blocks to be performed. A computer program can execute entirely on a machine, partly on a machine, as a stand-alone software package partly on a machine and partly on a remote machine or entirely on a remote machine or server.
In the context of the present invention, a computer-readable storage medium may be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. A computer readable storage medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. Alternatively, the computer readable storage medium may be a machine readable signal medium. More specific examples of a machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, a hard disk, a Random Access Memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a compact disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.
To provide for interaction with a user, the systems and techniques described here can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to a user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which a user can provide input to the electronic device. Other kinds of devices may also be used to provide for interaction with a user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form, including acoustic, speech, or tactile input.
The systems and techniques described here can be implemented in a computing system that includes a back-end component (e.g., as a data server), or that includes a middleware component (e.g., an application server), or that includes a front-end component (e.g., a user computer having a graphical user interface or a web browser through which a user can interact with an implementation of the systems and techniques described here), or any combination of such back-end, middleware, or front-end components. The components of the system can be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: local Area Networks (LANs), wide Area Networks (WANs), blockchain networks, and the Internet.
The computing system may include clients and servers. A client and server are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, also called a cloud computing server or a cloud host, and is a host product in a cloud computing service system, so that the defects of high management difficulty and weak service expansibility in the traditional physical host and VPS service are overcome.
It should be understood that various forms of the flows shown above may be used, with steps reordered, added, or deleted. For example, the steps described in the present invention may be executed in parallel, sequentially, or in different orders, and are not limited herein as long as the desired results of the technical solution of the present invention can be achieved.
The above-described embodiments should not be construed as limiting the scope of the invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions may be made in accordance with design requirements and other factors. Any modification, equivalent replacement, and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (10)
1. A wind power output prediction method is characterized by comprising the following steps:
acquiring historical data of target wind power output of a target wind power plant in a preset historical time period;
inputting the target wind power output historical data into a target wind power output prediction model to obtain target wind power output prediction data of the target wind power plant output by the target wind power output prediction model;
the target wind power output prediction model is obtained by performing parameter optimization on a wind power output prediction model to be optimized based on a sample wind power output prediction result and a differential evolution algorithm with a symmetric average absolute percentage error as a target function; and predicting the sample wind power output prediction result on the basis of the wind power output prediction model to be optimized on the sample wind power output historical data.
2. The method of claim 1, prior to inputting the target wind power output historical data into a target wind power output prediction model, comprising:
collecting sample wind power output historical data of a target wind power plant;
constructing a wind power output prediction model to be optimized, wherein the wind power output prediction model to be optimized comprises a CNN (convolutional network) and an LSTM (linear spline) prediction network;
inputting the historical data of the sample wind power output into the wind power output prediction model to be optimized to obtain a prediction result of the sample wind power output;
and performing parameter optimization on the CNN convolutional network and the LSTM prediction network based on the sample wind power output prediction result and a differential evolution algorithm taking a symmetric average absolute percentage error as a target function.
3. The method of claim 2, wherein the parameter optimizing the CNN convolutional network and the LSTM predictive network based on the sample wind power output prediction and a differential evolution algorithm with a symmetric mean absolute percentage error as a target function comprises:
adjusting a first parameter of the CNN based on the sample wind power output prediction result;
adjusting a second parameter of the LSTM prediction network based on the sample wind power output prediction result;
determining a symmetric average absolute percentage error of the sample wind power output prediction result and the sample wind power output historical data;
and determining the optimal parameters of the CNN network and the LSTM prediction network in the wind power output prediction model to be optimized according to a differential evolution algorithm taking the symmetric average absolute percentage error as a target function.
4. The method of claim 3, wherein said symmetrically averaging absolute percent errors comprises:
wherein: SMAPE is the mean absolute percent error of symmetry,
is sample wind power output prediction data, y i The data is sample wind power output historical data, and n is the data volume of the sample wind power output historical data.
5. The method of claim 3, wherein the first parameter comprises: learning rate, batch sample number and maximum iteration number in the CNN network;
the second parameter includes: LSTM predicts the number of hidden layer neurons, the drop rate, and the time lag order in the network.
6. The method of claim 2, wherein the CNN network is represented as:
O t ＝σ(W*x t +b)；
wherein W represents a convolution kernel; x is the number of t Representing a time sequence formed by second wind power output historical data of the target wind power plant; * Representing a discrete convolution operator; b represents a bias parameter; σ represents an activation function; o is t And representing feature data output after convolution operation.
7. A wind power output prediction device, comprising:
the target data acquisition module is used for acquiring target wind power output historical data of a target wind power plant in a preset historical time period;
the target data prediction module is used for inputting the target wind power output historical data into a target wind power output prediction model to obtain target wind power output prediction data of the target wind power plant output by the target wind power output prediction model;
the target wind power output prediction model is obtained by performing parameter optimization on a to-be-optimized wind power output prediction model based on a sample wind power output prediction result and a differential evolution algorithm; and predicting the sample wind power output prediction result on the basis of the wind power output prediction model to be optimized on the sample wind power output historical data.
8. The apparatus of claim 7, further comprising:
the sample data acquisition module is used for acquiring sample wind power output historical data of a target wind power plant before inputting the target wind power output historical data into the target wind power output prediction model;
the wind power output prediction model to be optimized is constructed by the prediction model construction module and comprises a CNN (convolutional network) and an LSTM (least Square TM) prediction network;
the sample data prediction module is used for inputting the historical wind power output data of the sample into the wind power output prediction model to be optimized to obtain a prediction result of the wind power output of the sample;
and the parameter optimization module is used for optimizing parameters of the CNN convolutional network and the LSTM prediction network based on the sample wind power output prediction result and a differential evolution algorithm taking a symmetric average absolute percentage error as a target function.
9. An electronic device, characterized in that the electronic device comprises:
at least one processor; and
a memory communicatively coupled to the at least one processor; wherein,
the memory stores a computer program executable by the at least one processor to enable the at least one processor to perform the wind power output prediction method of any of claims 1-6.
10. A computer-readable storage medium, wherein the computer-readable storage medium stores computer instructions for causing a processor to implement the wind power output prediction method according to any one of claims 1-6 when executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310028559.4A CN115983486A (en) | 2023-01-09 | 2023-01-09 | Wind power output prediction method and device, electronic equipment and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310028559.4A CN115983486A (en) | 2023-01-09 | 2023-01-09 | Wind power output prediction method and device, electronic equipment and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN115983486A true CN115983486A (en) | 2023-04-18 |
Family
ID=85972222
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310028559.4A Pending CN115983486A (en) | 2023-01-09 | 2023-01-09 | Wind power output prediction method and device, electronic equipment and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115983486A (en) |
-
2023
- 2023-01-09 CN CN202310028559.4A patent/CN115983486A/en active Pending
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109902801B (en) | Flood collective forecasting method based on variational reasoning Bayesian neural network | |
| CN117039895B (en) | Wind power prediction method and system for energy storage auxiliary black start | |
| CN110910004A (en) | Reservoir dispatching rule extraction method and system with multiple uncertainties | |
| CN108074015B (en) | Ultra-short-term prediction method and system for wind power | |
| CN116307215A (en) | Load prediction method, device, equipment and storage medium of power system | |
| CN116595394A (en) | Training method of wind speed correction model, wind speed prediction method, wind speed prediction equipment and medium | |
| CN113408808B (en) | Training method, data generation device, electronic equipment and storage medium | |
| CN116485031A (en) | Method, device, equipment and storage medium for predicting short-term power load | |
| CN118428754A (en) | New energy power generation input power prediction method and system | |
| CN117332898A (en) | New energy small time scale power time sequence rolling prediction method based on machine learning | |
| CN117332896A (en) | New energy small time scale power prediction method and system for multilayer integrated learning | |
| CN115952921A (en) | Photovoltaic energy power prediction method and device, electronic equipment and storage medium | |
| CN111476402A (en) | Wind power generation capacity prediction method coupling meteorological information and EMD technology | |
| CN115983486A (en) | Wind power output prediction method and device, electronic equipment and storage medium | |
| KR102539223B1 (en) | Deep learning method for accelerated processing of ami data stream in edge computing system | |
| CN113112092A (en) | Short-term probability density load prediction method, device, equipment and storage medium | |
| CN118468059B (en) | Power station characteristic determining method and device for electric power system, electronic equipment and medium | |
| CN118316023A (en) | Regional wind power probability prediction method and device, electronic equipment and storage medium | |
| CN115860249A (en) | Distributed photovoltaic power generation power prediction method, device, equipment and medium | |
| CN114626636A (en) | Power grid load prediction method and device, modeling method, computer equipment and medium | |
| CN116957133A (en) | Wind power generation power and photovoltaic power generation power prediction method and device | |
| CN117477548A (en) | Method and device for reconstructing power distribution network, electronic equipment and storage medium | |
| CN118151037A (en) | Method, device, equipment and storage medium for evaluating health state of lead-acid battery | |
| CN117422259A (en) | Distributed resource prediction aggregation method, device, equipment and storage medium | |
| CN114757444A (en) | Wind power 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 |