CN116805782A - New energy output scene generation method and device and computer equipment - Google Patents
New energy output scene generation method and device and computer equipment Download PDFInfo
- Publication number
- CN116805782A CN116805782A CN202310580416.4A CN202310580416A CN116805782A CN 116805782 A CN116805782 A CN 116805782A CN 202310580416 A CN202310580416 A CN 202310580416A CN 116805782 A CN116805782 A CN 116805782A
- Authority
- CN
- China
- Prior art keywords
- new energy
- curve
- time
- frequency part
- power
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 42
- 230000015654 memory Effects 0.000 claims abstract description 46
- 238000010248 power generation Methods 0.000 claims abstract description 39
- 238000007781 pre-processing Methods 0.000 claims abstract description 12
- 238000000354 decomposition reaction Methods 0.000 claims description 51
- 230000006870 function Effects 0.000 claims description 40
- 230000008859 change Effects 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 8
- 238000012545 processing Methods 0.000 claims description 8
- 238000005070 sampling Methods 0.000 claims description 8
- 230000009466 transformation Effects 0.000 claims description 8
- 239000011159 matrix material Substances 0.000 claims description 4
- 238000004091 panning Methods 0.000 claims description 4
- 230000008901 benefit Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 230000007787 long-term memory Effects 0.000 description 4
- 230000008569 process Effects 0.000 description 4
- 238000012986 modification Methods 0.000 description 3
- 230000004048 modification Effects 0.000 description 3
- 230000006403 short-term memory Effects 0.000 description 3
- 238000004891 communication Methods 0.000 description 2
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000003912 environmental pollution Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application discloses a method, a device and computer equipment for generating a new energy output scene, belongs to the technical field of power systems, and solves the problems that a predicted scene generated by a traditional probability statistics method has a larger error with a real scene and the reliability of the predicted scene is lower at present. The method comprises the following steps: the method comprises the steps of obtaining historical power data of new energy, preprocessing the historical power data, extracting a time-varying curve of a target low-frequency part of new energy power generation and a time-varying curve of a target high-frequency part of new energy power generation, obtaining a plurality of prediction curves based on the time-varying curve of the target low-frequency part of the new energy power generation by using a long-short-period memory network LSTM, and superposing the plurality of prediction curves by using the time-varying curve of the target low-frequency part to obtain a plurality of target prediction curves for representing a new energy output scene.
Description
Technical Field
The application belongs to the technical field of power systems, and particularly relates to a method and a device for generating a new energy output scene, computer equipment and a readable storage medium.
Background
Along with the continuous increase of global energy demands, the problems of resource shortage, environmental pollution, climate change and the like are increasingly highlighted due to the large-scale development of traditional energy, so that the new energy ratio is gradually increased. The intermittence and randomness of the new energy output seriously affect the stable operation of the power system, and have important influence on future planning, annual planning and calculation of the flexibility requirement of the power system, and how to describe the uncertainty of the renewable energy output is the key to overcome the problems.
The existing method mainly generates a plurality of typical scenes which possibly occur in the future through a traditional probability statistics method, and analyzes each scene so as to plan and calculate the demand; the applicant realizes that the nature of the unified probability statistics method is that modeling of joint probability density distribution in a random process can only process data with smaller dimension, and processing capacity of nonlinear mapping problem is weak, and nonlinear relation between big data is difficult to capture, so that larger error exists between a generated prediction scene and a real scene, and reliability of the prediction scene is low.
Disclosure of Invention
In view of the above, the present application provides a method, a device, a computer device and a readable storage medium for generating a new energy output scene, which mainly aims to solve the problem that a prediction scene generated by a traditional probability statistics method has a larger error with a real scene and the reliability of the prediction scene is lower.
According to a first aspect of the present application, there is provided a method for generating a new energy output scenario, including:
acquiring historical power data of new energy, preprocessing the historical power data, and extracting a time-varying curve of a target low-frequency part and a time-varying curve of a target high-frequency part of the power generated by the new energy;
obtaining a plurality of prediction curves by utilizing a long-short-period memory network LSTM based on a curve of the target low-frequency part of the new energy power generation along with the time, wherein the prediction curves are curves of the new energy power generation along with the time;
and superposing the plurality of prediction curves by utilizing the curve of the target high-frequency part changing along with time to obtain a plurality of target prediction curves for representing the new energy output scene.
Optionally, the preprocessing the historical power data, extracting a time-varying curve of a target low-frequency part and a time-varying curve of a target high-frequency part of the new energy generated power, includes:
determining a first expression of a discrete wavelet sequence and a second expression of a discrete wavelet transform coefficient, wherein the first expression and the second expression are respectively:
equation 1:
where j represents the j-th decomposition level, k represents a parameter used to perform a panning operation in wavelet transform, a 0 B is the lowest resolution low frequency information 0 Is the detail information with the lowest resolution, psi is a wavelet mother function, t is time, and psi j,k (t) is the discrete wavelet sequence;
equation 2:
wherein ,Cj,k F (t) is a signal to be analyzed for the discrete wavelet transform coefficient;
constructing a reconstruction formula based on the first expression and the second expression, the reconstruction formula expressed as:
equation 3:
wherein C is a constant and f' (t) is a discrete signal;
performing wavelet decomposition on the historical power data to obtain a decomposition formula, wherein the decomposition formula is as follows:
equation 4:
wherein ,An Is the low frequency part of the nth decomposition layer, D l For the high frequency part of the first hierarchical level, l=1, 2, …, n, S is the original discrete signal;
performing discrete wavelet transformation on the reconstruction formula based on the decomposition formula to obtain a discrete wavelet reconstruction function, wherein the discrete wavelet reconstruction function is expressed as:
equation 5:
wherein f "(t) is the discrete wavelet reconstruction function, d j,k ＝<f(t),ψ j,k (t)>Is the wavelet coefficient phi j,k (t) is a scaling function;
determining the number of decomposition layers, and determining a time-varying curve of a target low-frequency part and a time-varying curve of a target high-frequency part of the new energy power generation based on the number of decomposition layers and the discrete wavelet reconstruction function.
Optionally, the discrete wavelet transformation is performed on the reconstruction formula based on the decomposition formula to obtain a discrete wavelet reconstruction function, including:
projecting the reconstruction function to a low-frequency part of a decomposition layer j to obtain a profile signal under the j scale, wherein the profile signal under the j scale is expressed as:
equation 6:
wherein ,cj,k Is a scale factor, and c j,k ＝<f(t),φ j,k (t)>，Is the profile signal at the j scale;
projecting the reconstruction function to the high-frequency part of the decomposition layer j to obtain a detail signal under the j scale, wherein the detail signal under the j scale is expressed as:
equation 7:
wherein ,a detail signal at the j scale;
determining a decomposition layer number, and determining the discrete wavelet reconstruction function based on the decomposition layer number, the profile signal at the j scale and the detail signal at the j scale.
Optionally, the obtaining a plurality of prediction curves based on the curve of the target low-frequency part of the new energy generated power changing along with time by using a long-short-period memory network LSTM includes:
predicting a time-varying curve of a target low-frequency part of the new energy power generation power by utilizing the long-short-period memory network LSTM to obtain a probability distribution curve of a predicted power error;
and determining a probability distribution curve of the predicted power based on a time-varying curve of a target low-frequency part of the new energy power generation, and generating a plurality of prediction curves by adopting the long-short-period memory network LSTM according to the probability distribution curve of the predicted power and the probability distribution curve of the predicted power error.
Optionally, the predicting, by using the long-short-term memory network LSTM, a time-varying curve of the target low-frequency portion of the generated power of the new energy source to obtain a probability distribution curve of a predicted power error includes:
extracting a plurality of points from a curve of the target low-frequency part of the new energy power generation along with the time change, and determining a characteristic value of each point in the plurality of points, wherein the characteristic value is one of a valley value, a peak value curve and a curve slope;
and inputting the characteristic value of each point in the plurality of points into the long-short-period memory network LSTM to obtain the probability distribution curve of the predicted power error.
Optionally, the determining the probability distribution curve of the predicted power based on the curve of the target low-frequency part of the new energy generated power over time includes:
extracting a plurality of points from a curve of the target low-frequency part of the new energy power generation along with the time change, and determining a characteristic value of each point in the plurality of points, wherein the characteristic value is one of a valley value, a peak value curve and a slope of the curve;
and fitting the characteristic value of each point in the plurality of points by using a matrix laboratory MATLAB tool to obtain a probability distribution curve of the predicted power.
Optionally, the generating the plurality of prediction curves according to the probability distribution curve of the predicted power and the probability distribution curve of the predicted power error by using the long-short-period memory network LSTM includes:
randomly sampling the probability distribution curve of the predicted power to obtain the probability of the predicted power corresponding to each first input point in a plurality of first input points;
randomly sampling the probability distribution curve of the predicted power error to obtain the probability of the predicted power error corresponding to each second input point in the plurality of second input points;
and inputting the probability of the predicted power corresponding to each first input point of the plurality of first input points and the probability of the predicted power error corresponding to each second input point of the plurality of second input points into a long-short-period memory network LSTM, and generating the plurality of prediction curves.
According to a second aspect of the present application, there is provided a device for generating a new energy output scenario, including:
the processing module is used for acquiring historical power data of the new energy, preprocessing the historical power data and extracting a time-varying curve of a target low-frequency part and a time-varying curve of a target high-frequency part of the power generation power of the new energy;
the acquisition module is used for acquiring a plurality of prediction curves by utilizing a long-short-period memory network LSTM based on the curve of the target low-frequency part of the new energy power generation along with time, wherein the prediction curves are curves of the new energy power generation along with time;
and the superposition module is used for superposing the plurality of prediction curves by utilizing the curve of the target high-frequency part changing along with time to obtain a plurality of superposition curves as a plurality of target prediction curves for representing the new energy output scene.
According to a third aspect of the present application there is provided a computer device comprising a memory storing a computer program and a processor implementing the steps of the method of any of the first aspects described above when the computer program is executed by the processor.
According to a fourth aspect of the present application there is provided a readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of any of the first aspects described above.
By means of the technical scheme, the application provides a new energy output scene generation method, which comprises the steps of preprocessing acquired historical power data of new energy, extracting a time-varying curve of a target low-frequency part of new energy power generation and a time-varying curve of a target high-frequency part, obtaining a plurality of prediction curves by using a long-short-period memory network LSTM based on the time-varying curve of the target low-frequency part of the new energy power generation, and finally superposing the plurality of prediction curves by using the time-varying curve of the target high-frequency part to obtain a plurality of target prediction curves for representing the new energy output scene; the long-term and short-term memory network LSTM can effectively record data of a period before, can capture time sequence relations among output data of new energy, enables the generated scene effect to be better, and improves the reliability of the predicted scene.
The foregoing description is only an overview of the present application, and is intended to be implemented in accordance with the teachings of the present application in order that the same may be more clearly understood and to make the same and other objects, features and advantages of the present application more readily apparent.
Drawings
Various other advantages and benefits will become apparent to those of ordinary skill in the art upon reading the following detailed description of the preferred embodiments. The drawings are only for purposes of illustrating the preferred embodiments and are not to be construed as limiting the application. Also, like reference numerals are used to designate like parts throughout the figures. In the drawings:
fig. 1 shows a flowchart of a method for generating a new energy output scenario according to an embodiment of the present application.
Fig. 2 shows an analysis diagram of a long-short-term memory network LSTM of a new energy output scenario generation method according to an embodiment of the present application.
Fig. 3 is a schematic diagram of a prediction curve of wind power generation power of a new energy output scenario generation method according to an embodiment of the present application.
Fig. 4 is a schematic diagram of a plurality of wind power output curves of a method for generating a new energy output scenario according to an embodiment of the present application.
Fig. 5 shows a schematic structural diagram of a generating device for a new energy output scenario according to an embodiment of the present application.
Fig. 6 shows a schematic device structure of a computer device according to an embodiment of the present application.
Detailed Description
Various aspects and features of the present application are described herein with reference to the accompanying drawings.
It should be understood that various modifications may be made to the embodiments of the application herein. Therefore, the above description should not be taken as limiting, but merely as exemplification of the embodiments. Other modifications within the scope and spirit of the application will occur to persons of ordinary skill in the art.
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments of the application and, together with a general description of the application given above, and the detailed description of the embodiments given below, serve to explain the principles of the application.
These and other characteristics of the application will become apparent from the following description of a preferred form of embodiment, given as a non-limiting example, with reference to the accompanying drawings.
It is also to be understood that, although the application has been described with reference to some specific examples, those skilled in the art can certainly realize many other equivalent forms of the application.
The above and other aspects, features and advantages of the present application will become more apparent in light of the following detailed description when taken in conjunction with the accompanying drawings.
Specific embodiments of the present application will be described hereinafter with reference to the accompanying drawings; however, it is to be understood that the disclosed embodiments are merely exemplary of the application, which can be embodied in various forms. Well-known and/or repeated functions and constructions are not described in detail to avoid obscuring the application in unnecessary or unnecessary detail. Therefore, specific structural and functional details disclosed herein are not intended to be limiting, but merely as a basis for the claims and as a representative basis for teaching one skilled in the art to variously employ the present application in virtually any appropriately detailed structure.
The specification may use the word "in one embodiment," "in another embodiment," "in yet another embodiment," or "in other embodiments," which may each refer to one or more of the same or different embodiments in accordance with the application.
The embodiment of the application provides a method for generating a new energy output scene, as shown in fig. 1, comprising the following steps:
101. and acquiring historical power data of the new energy, preprocessing the historical power data, and extracting a time-varying curve of a target low-frequency part and a time-varying curve of a target high-frequency part of the power generated by the new energy.
102. And obtaining a plurality of prediction curves by utilizing a long-short-period memory network LSTM based on the curve of the target low-frequency part of the new energy power generation along with the time change.
In the embodiment of the application, the prediction curve is a curve of the new energy predicted power generation changing with time.
103. And superposing a plurality of prediction curves by utilizing the curve of the target frequency part changing along with time to obtain a plurality of target prediction curves for representing the new energy output scene.
The method provided by the embodiment of the application comprises the steps of preprocessing the acquired historical power data of the new energy, extracting a time-varying curve of a target low-frequency part of the power generated by the new energy and a time-varying curve of a target high-frequency part of the power generated by the new energy, obtaining a plurality of prediction curves by utilizing a long-short-period memory network LSTM based on the time-varying curve of the target low-frequency part of the power generated by the new energy, and finally superposing the plurality of prediction curves by utilizing the time-varying curve of the target high-frequency part to obtain a plurality of target prediction curves for representing the power output scene of the new energy; the long-term and short-term memory network LSTM can effectively record data of a period before, can capture time sequence relations among output data of new energy, enables the generated scene effect to be better, and improves the reliability of the predicted scene.
Further, as a refinement and expansion of the specific implementation manner of the above embodiment, in order to fully describe the specific implementation process of the embodiment, the embodiment of the present application provides another method for generating a new energy output scenario, where the method includes:
201. and acquiring historical power data of the new energy, preprocessing the historical power data, and extracting a time-varying curve of a target low-frequency part and a time-varying curve of a target high-frequency part of the power generated by the new energy.
In the embodiment of the application, after the historical power data of the new energy is acquired, a first expression of a discrete wavelet sequence and a second expression of a discrete wavelet transformation coefficient are determined, wherein the first expression and the second expression are respectively:
equation 1:
where j represents the j-th decomposition level, k represents a parameter used to perform a panning operation in wavelet transform, a 0 B is the lowest resolution low frequency information 0 Is the detail information with the lowest resolution, psi is a wavelet mother function, t is time, and psi j,k (t) is a discrete wavelet sequence;
equation 2:
wherein ,Cj,k F (t) is a signal to be analyzed for the discrete wavelet transform coefficient;
constructing a reconstruction formula based on the first expression and the second expression, the reconstruction formula being expressed as:
equation 3:
wherein C is a constant and f' (t) is a discrete signal;
performing wavelet decomposition on the historical power data to obtain a decomposition formula, wherein the decomposition formula is as follows:
equation 4:
wherein ,An Is the low frequency part of the nth decomposition layer, D l For the high frequency part of the first hierarchical level, l=1, 2, …, n, S is the original discrete signal; it should be noted that, as shown in fig. 2, the original discrete signal is decomposed into a plurality of sums of D signals and a signals after being subjected to discrete wavelet transform.
Performing discrete wavelet transformation on the reconstruction formula based on the decomposition formula to obtain a discrete wavelet reconstruction function, wherein the discrete wavelet reconstruction function is expressed as:
equation 5:
wherein f'(t) is a discrete wavelet reconstruction function, d j,k ＝<f(t),ψ j,k (t)>Is the wavelet coefficient phi j,k (t) is a scaling function;
determining the number of decomposition layers, and determining a time-varying curve of a target low-frequency part and a time-varying curve of a target high-frequency part of the new energy power generation based on the number of decomposition layers and a discrete wavelet reconstruction function.
Further, discrete wavelet transformation is performed on the reconstruction formula based on the decomposition formula to obtain a discrete wavelet reconstruction function, and the specific steps are as follows:
projecting the reconstruction function to the low-frequency part of the decomposition layer j to obtain a profile signal under the j scale, wherein the profile signal under the j scale is expressed as:
equation 6:
wherein ,cj,k Is a scale factor, and c j,k ＝<f(t),φ j,k (t)>，Is a profile signal at the j scale;
projecting the reconstruction function to a high-frequency part of the decomposition layer j to obtain a detail signal under the j scale, wherein the detail signal under the j scale is expressed as:
equation 7:
wherein ,is a detail signal at the j scale;
the number of decomposition layers is determined and a discrete wavelet reconstruction function is determined based on the number of decomposition layers, the profile signal at the j-scale and the detail signal at the j-scale.
202. And obtaining a plurality of prediction curves by utilizing a long-short-period memory network LSTM based on the curve of the target low-frequency part of the new energy power generation along with the time change.
In the embodiment of the application, a long-short-term memory network LSTM is used to predict a time-varying curve of a target low-frequency part, that is, a plurality of inputs are firstly determined, for example, 10 consecutive days are taken as one input, the long-short-term memory network LSTM is a time-cycled neural network, an analysis chart of which is shown in fig. 3, wherein 3 types of gates, namely, an input gate, a forgetting gate and an output gate, and memory cells with the same shape as a hidden state are introduced, specifically, assuming that the number of hidden units is h, a small batch of inputs Xt epsilon Rn×d (the number of samples is n, the number of inputs is d) of a given time step t and a hidden state Ht-1 epsilon Rn×h of a previous time step are assumed. The input gate It e Rn×h, the forget gate Ft e Rn×h and the output gate Ot e Rn×h of time step t are calculated as follows:
It＝σ(XtWxi+Ht-1Whi+bi)，
Ft＝σ(XtWxf+Ht-1Whf+bf)，
Ot＝σ(XtWxo+Ht-1Who+bo)，
wherein Wxi, wxf, wxo, whi, whf, and wha epsilon, rh×h, wxi, wxf, wxo, and Whi, whf, who are weight parameters, bi epsilon, R1×h, bf epsilon, R1×h, bo epsilon, R1×h, bi, bf, and bo are bias parameters.
Specifically, firstly, a long-short-period memory network LSTM is utilized to predict a time-varying curve of a target low-frequency part of new energy power generation to obtain a probability distribution curve of a predicted power error, then a probability distribution curve of the predicted power is determined based on the time-varying curve of the target low-frequency part of the new energy power generation, and a plurality of prediction curves are generated by adopting the long-short-period memory network LSTM according to the probability distribution curve of the predicted power and the probability distribution curve of the predicted power error, wherein the prediction curves are curves of the new energy predicted power variation with time. Illustratively, the predicted curve of wind power generation power is shown in fig. 3, with the ordinate being the predicted power of wind power generation and the abscissa being time.
Further, the long-term memory network LSTM is utilized to predict the time-varying curve of the target low-frequency part of the new energy power generation power, and a probability distribution curve of a predicted power error is obtained, and the specific steps are as follows: firstly, extracting a plurality of points from a curve of a target low-frequency part of new energy generated power changing along with time, determining a characteristic value of each point in the plurality of points, wherein the characteristic value is one of a valley value, a peak value curve and a curve slope, and then inputting the characteristic value of each point in the plurality of points into a long-short-period memory network LSTM to obtain a probability distribution curve of a predicted power error.
Further, determining a probability distribution curve of the predicted power based on a curve of the target low-frequency part of the new energy generated power changing with time, wherein the probability distribution curve comprises the following specific steps: firstly, extracting a plurality of points from a time-varying curve of a target low-frequency part of new energy generated power, determining a characteristic value of each point in the plurality of points, wherein the characteristic value is one of a valley value, a peak value curve and a slope of the curve, and then fitting the characteristic value of each point in the plurality of points by using a matrix laboratory MATLAB tool to obtain a probability distribution curve of predicted power.
Further, a plurality of prediction curves are generated by adopting a long-short-period memory network LSTM according to the probability distribution curve of the predicted power and the probability distribution curve of the predicted power error, and the specific steps are as follows: randomly sampling the probability distribution curve of the predicted power to obtain the probability of the predicted power corresponding to each first input point in the plurality of first input points, randomly sampling the probability distribution curve of the predicted power error to obtain the probability of the predicted power error corresponding to each second input point in the plurality of second input points, and then inputting the probability of the predicted power corresponding to each first input point in the plurality of first input points and the probability of the predicted power error corresponding to each second input point in the plurality of second input points into the long-short-term memory network LSTM to generate a plurality of predicted curves.
203. And superposing a plurality of prediction curves by utilizing the curve of the target frequency part changing along with time to obtain a plurality of target prediction curves for representing the new energy output scene.
In the embodiment of the application, after a plurality of prediction curves are overlapped by utilizing the curves of the target frequency part changing along with time, a plurality of overlapped prediction curves are obtained, the overlapped prediction curves are the curves of the target new energy predicted power changing along with time, and the overlapped prediction curves are used as the target prediction curves for representing the new energy output scene. Illustratively, as shown in FIG. 4, a plurality of wind power output curves, that is, curves of wind power predicted generation power over time are generated, with the ordinate being power and the abscissa being time.
According to the method provided by the embodiment of the application, wavelet transformation is introduced, the main trend of the data is extracted firstly, and then scene generation is carried out, so that the long-short-term memory network LSTM in deep learning is used, the data of a period before can be effectively recorded by the long-short-term memory network LSTM, the time sequence relation between the output data of new energy sources can be captured, the generated scene effect is better, and the reliability of the predicted scene is improved.
Further, as shown in fig. 5, as a specific implementation of the method shown in fig. 1, an embodiment of the present application provides a device for generating a new energy output scenario, including: a processing module 301, an acquisition module 302 and a superposition module 303.
The processing module 301 is configured to obtain historical power data of a new energy, pre-process the historical power data, and extract a time-varying curve of a target low-frequency portion and a time-varying curve of a target high-frequency portion of power generated by the new energy;
the obtaining module 302 is configured to obtain a plurality of prediction curves by using the long-short-period memory network LSTM based on a time-varying curve of the target low-frequency portion of the new energy generated power, where the prediction curves are time-varying curves of the new energy predicted generated power;
the superposition module 303 is configured to superimpose the plurality of prediction curves by using a curve of the target frequency portion that changes with time, so as to obtain a plurality of superimposed curves as a plurality of target prediction curves for representing the new energy output scenario.
In a specific application scenario, the processing module 301 is further configured to:
determining a first expression of the discrete wavelet sequence and a second expression of the discrete wavelet transform coefficient, wherein the first expression and the second expression are respectively:
equation 1:
where j represents the j-th decomposition level, k represents a parameter used to perform a panning operation in wavelet transform, a 0 B is the lowest resolution low frequency information 0 Is the detail information with the lowest resolution, psi is a wavelet mother function, t is time, and psi j,k (t) is a discrete wavelet sequence;
equation 2:
wherein ,Cj,k F (t) is a signal to be analyzed and is a discrete wavelet transform coefficient;
constructing a reconstruction formula based on the first expression and the second expression, the reconstruction formula being expressed as:
equation 3:
wherein C is a constant and f' (t) is a discrete signal;
performing wavelet decomposition on the historical power data to obtain a decomposition formula, wherein the decomposition formula is as follows:
equation 4:
wherein ,An Is the low frequency part of the nth decomposition layer, D l For the high frequency part of the first hierarchical level, l=1, 2, …, n, S is the original discrete signal;
performing discrete wavelet transformation on the reconstruction formula based on the decomposition formula to obtain a discrete wavelet reconstruction function, wherein the discrete wavelet reconstruction function is expressed as:
equation 5:
wherein f "(t) is a discrete waveletReconstructing the function, d j,k ＝<f(t),ψ j,k (t)>Is the wavelet coefficient phi j,k (t) is a scaling function;
determining the number of decomposition layers, and determining a time-varying curve of a target low-frequency part and a time-varying curve of a target high-frequency part of the new energy power generation based on the number of decomposition layers and a discrete wavelet reconstruction function.
In a specific application scenario, the processing module 301 is further configured to:
projecting the reconstruction function to the low-frequency part of the decomposition layer j to obtain a profile signal under the j scale, wherein the profile signal under the j scale is expressed as:
equation 6:
wherein ,cj,k Is a scale factor, and c j,k ＝<f(t),φ j,k (t)>，Is a profile signal at the j scale;
projecting the reconstruction function to a high-frequency part of the decomposition layer j to obtain a detail signal under the j scale, wherein the detail signal under the j scale is expressed as:
equation 7:
wherein ,is a detail signal at the j scale;
the number of decomposition layers is determined and a discrete wavelet reconstruction function is determined based on the number of decomposition layers, the profile signal at the j-scale and the detail signal at the j-scale.
In a specific application scenario, the obtaining module 302 is further configured to: predicting a time-varying curve of a target low-frequency part of the new energy generated power by utilizing a long-short-period memory network LSTM to obtain a probability distribution curve of a predicted power error; and determining a probability distribution curve of the predicted power based on a time-varying curve of a target low-frequency part of the new energy power generation power, and generating a plurality of prediction curves by adopting a long-short-period memory network LSTM according to the probability distribution curve of the predicted power and the probability distribution curve of the predicted power error.
In a specific application scenario, the obtaining module 302 is further configured to: extracting a plurality of points from a curve of the target low-frequency part of the new energy power generation with time, and determining a characteristic value of each point in the plurality of points, wherein the characteristic value is one of a valley value, a peak value curve and a curve slope; and inputting the characteristic value of each point in the plurality of points into a long-short-period memory network LSTM to obtain a probability distribution curve of the predicted power error.
In a specific application scenario, the obtaining module 302 is further configured to: extracting a plurality of points from a curve of the target low-frequency part of the new energy power generation along with the change of time, and determining a characteristic value of each point in the plurality of points, wherein the characteristic value is one of a valley value, a peak value curve and a slope of the curve; fitting the characteristic value of each point in the plurality of points by using a matrix laboratory MATLAB tool to obtain a probability distribution curve of the predicted power.
In a specific application scenario, the obtaining module 302 is further configured to: randomly sampling a probability distribution curve of the predicted power to obtain the probability of the predicted power corresponding to each first input point in the plurality of first input points; randomly sampling a probability distribution curve of the predicted power error to obtain the probability of the predicted power error corresponding to each second input point in the plurality of second input points; and inputting the probability of the predicted power corresponding to each first input point in the plurality of first input points and the probability of the predicted power error corresponding to each second input point in the plurality of second input points into a long-short-period memory network LSTM, and generating a plurality of prediction curves.
According to the device provided by the embodiment of the application, the processing module is used for preprocessing the acquired historical power data of the new energy, extracting the time-varying curve of the target low-frequency part and the time-varying curve of the target high-frequency part of the power generated by the new energy, obtaining a plurality of prediction curves by using the long-short-period memory network LSTM based on the time-varying curve of the target low-frequency part of the power generated by the new energy through the acquisition module, and finally superposing the plurality of prediction curves by using the time-varying curve of the target high-frequency part through the superposition module to obtain a plurality of target prediction curves for representing the power output scene of the new energy; the long-term and short-term memory network LSTM can effectively record data of a period before, can capture time sequence relations among output data of new energy, enables the generated scene effect to be better, and improves the reliability of the predicted scene.
In an exemplary embodiment, referring to fig. 6, there is also provided a computer device including a bus, a processor, a memory, and a communication interface, and may further include an input-output interface and a display device, where each functional unit may perform communication with each other through the bus. The memory stores a computer program and a processor, which is used for executing the program stored in the memory and executing the method for generating the new energy output scene in the embodiment.
A readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of the method of generating a new energy output scenario.
From the above description of the embodiments, it will be clear to those skilled in the art that the present application may be implemented in hardware, or may be implemented by means of software plus necessary general hardware platforms. Based on such understanding, the technical solution of the present application may be embodied in the form of a software product, which may be stored in a non-volatile storage medium (may be a CD-ROM, a U-disk, a mobile hard disk, etc.), and includes several instructions for causing a computer device (may be a personal computer, a server, or a network device, etc.) to execute the method described in the respective implementation scenario of the present application.
Those skilled in the art will appreciate that the drawing is merely a schematic illustration of a preferred implementation scenario and that the modules or flows in the drawing are not necessarily required to practice the application.
Those skilled in the art will appreciate that modules in an apparatus in an implementation scenario may be distributed in an apparatus in an implementation scenario according to an implementation scenario description, or that corresponding changes may be located in one or more apparatuses different from the implementation scenario. The modules of the implementation scenario may be combined into one module, or may be further split into a plurality of sub-modules.
The above-mentioned inventive sequence numbers are merely for description and do not represent advantages or disadvantages of the implementation scenario.
The above embodiments are only exemplary embodiments of the present application and are not intended to limit the present application, the scope of which is defined by the claims. Various modifications and equivalent arrangements of this application will occur to those skilled in the art, and are intended to be within the spirit and scope of the application.
Claims (10)
1. The method for generating the new energy output scene is characterized by comprising the following steps of:
acquiring historical power data of new energy, preprocessing the historical power data, and extracting a time-varying curve of a target low-frequency part and a time-varying curve of a target high-frequency part of the power generated by the new energy;
obtaining a plurality of prediction curves by utilizing a long-short-period memory network LSTM based on a curve of the target low-frequency part of the new energy power generation along with the time, wherein the prediction curves are curves of the new energy power generation along with the time;
and superposing the plurality of prediction curves by utilizing the curve of the target high-frequency part changing along with time to obtain a plurality of target prediction curves for representing the new energy output scene.
2. The method of claim 1, wherein the preprocessing the historical power data to extract a time-varying curve of a target low-frequency portion and a time-varying curve of a target high-frequency portion of the generated power of the new energy comprises:
determining a first expression of a discrete wavelet sequence and a second expression of a discrete wavelet transform coefficient, wherein the first expression and the second expression are respectively:
equation 1:
where j represents the j-th decomposition level, k represents a parameter used to perform a panning operation in wavelet transform, a 0 B is the lowest resolution low frequency information 0 Is the detail information with the lowest resolution, psi is a wavelet mother function, t is time, and psi j,k (t) is the discrete wavelet sequence;
equation 2:
wherein ,Cj,k F (t) is a signal to be analyzed for the discrete wavelet transform coefficient;
constructing a reconstruction formula based on the first expression and the second expression, the reconstruction formula expressed as:
equation 3:
wherein C is a constant and f' (t) is a discrete signal;
performing wavelet decomposition on the historical power data to obtain a decomposition formula, wherein the decomposition formula is as follows:
equation 4:
wherein ,An Is the low frequency part of the nth decomposition layer, D l For the high frequency part of the first hierarchical level, l=1, 2, …, n, S is the original discrete signal;
performing discrete wavelet transformation on the reconstruction formula based on the decomposition formula to obtain a discrete wavelet reconstruction function, wherein the discrete wavelet reconstruction function is expressed as:
equation 5:
wherein f "(t) is the discrete wavelet reconstruction function, d j,k ＝<f(t),ψ j,k (t)>Is the wavelet coefficient phi j,k (t) is a scaling function;
determining the number of decomposition layers, and determining a time-varying curve of a target low-frequency part and a time-varying curve of a target high-frequency part of the new energy power generation based on the number of decomposition layers and the discrete wavelet reconstruction function.
3. The method of generating a new energy output scenario according to claim 2, wherein the performing discrete wavelet transform on the reconstruction formula based on the decomposition formula to obtain a discrete wavelet reconstruction function includes:
projecting the reconstruction function to a low-frequency part of a decomposition layer j to obtain a profile signal under the j scale, wherein the profile signal under the j scale is expressed as:
equation 6:
wherein ,cj,k Is a scale factor, and c j,k ＝<f(t),φ j,k (t)>，Is the profile signal at the j scale;
projecting the reconstruction function to the high-frequency part of the decomposition layer j to obtain a detail signal under the j scale, wherein the detail signal under the j scale is expressed as:
equation 7:
wherein ,a detail signal at the j scale;
determining a decomposition layer number, and determining the discrete wavelet reconstruction function based on the decomposition layer number, the profile signal at the j scale and the detail signal at the j scale.
4. The method of claim 1, wherein the generating the plurality of prediction curves based on the time-varying curve of the target low frequency portion of the generated power of the new energy using the long-short-term memory network LSTM comprises:
predicting a time-varying curve of a target low-frequency part of the new energy power generation power by utilizing the long-short-period memory network LSTM to obtain a probability distribution curve of a predicted power error;
and determining a probability distribution curve of the predicted power based on a time-varying curve of a target low-frequency part of the new energy power generation, and generating a plurality of prediction curves by adopting the long-short-period memory network LSTM according to the probability distribution curve of the predicted power and the probability distribution curve of the predicted power error.
5. The method for generating a new energy output scenario according to claim 3, wherein predicting a time-varying curve of the target low-frequency portion of the new energy generated power by using the long-short-term memory network LSTM to obtain a probability distribution curve of a predicted power error includes:
extracting a plurality of points from a curve of the target low-frequency part of the new energy power generation along with the time change, and determining a characteristic value of each point in the plurality of points, wherein the characteristic value is one of a valley value, a peak value curve and a curve slope;
and inputting the characteristic value of each point in the plurality of points into the long-short-period memory network LSTM to obtain the probability distribution curve of the predicted power error.
6. The method of claim 3, wherein determining the probability distribution curve of the predicted power based on the curve of the target low-frequency portion of the generated power of the new energy over time comprises:
extracting a plurality of points from a curve of the target low-frequency part of the new energy power generation along with the time change, and determining a characteristic value of each point in the plurality of points, wherein the characteristic value is one of a valley value, a peak value curve and a slope of the curve;
and fitting the characteristic value of each point in the plurality of points by using a matrix laboratory MATLAB tool to obtain a probability distribution curve of the predicted power.
7. The method of claim 3, wherein the generating the plurality of prediction curves using the long-short term memory network LSTM according to the probability distribution curve of the predicted power and the probability distribution curve of the predicted power error comprises:
randomly sampling the probability distribution curve of the predicted power to obtain the probability of the predicted power corresponding to each first input point in a plurality of first input points;
randomly sampling the probability distribution curve of the predicted power error to obtain the probability of the predicted power error corresponding to each second input point in the plurality of second input points;
and inputting the probability of the predicted power corresponding to each first input point of the plurality of first input points and the probability of the predicted power error corresponding to each second input point of the plurality of second input points into a long-short-period memory network LSTM, and generating the plurality of prediction curves.
8. The utility model provides a generating device of new forms of energy output scene which characterized in that includes:
the processing module is used for acquiring historical power data of the new energy, preprocessing the historical power data and extracting a time-varying curve of a target low-frequency part and a time-varying curve of a target high-frequency part of the power generation power of the new energy;
the acquisition module is used for acquiring a plurality of prediction curves by utilizing a long-short-period memory network LSTM based on the curve of the target low-frequency part of the new energy power generation along with time, wherein the prediction curves are curves of the new energy power generation along with time;
and the superposition module is used for superposing the plurality of prediction curves by utilizing the curve of the target high-frequency part changing along with time to obtain a plurality of superposition curves as a plurality of target prediction curves for representing the new energy output scene.
9. A computer device comprising a memory and a processor, the memory storing a computer program, characterized in that the processor implements the steps of the method of any of claims 1 to 7 when the computer program is executed.
10. A readable storage medium having stored thereon a computer program, which when executed by a processor realizes the steps of the method according to any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310580416.4A CN116805782A (en) | 2023-05-22 | 2023-05-22 | New energy output scene generation method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310580416.4A CN116805782A (en) | 2023-05-22 | 2023-05-22 | New energy output scene generation method and device and computer equipment |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN116805782A true CN116805782A (en) | 2023-09-26 |
Family
ID=88080154
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310580416.4A Pending CN116805782A (en) | 2023-05-22 | 2023-05-22 | New energy output scene generation method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116805782A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117424290A (en) * | 2023-10-07 | 2024-01-19 | 国家电网有限公司华东分部 | New energy source inclusion proportion calculating method, device, equipment and storage medium |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109214566A (en) * | 2018-08-30 | 2019-01-15 | 华北水利水电大学 | Short-term wind power prediction method based on shot and long term memory network |
| CN109214575A (en) * | 2018-09-12 | 2019-01-15 | 河海大学 | A kind of super short-period wind power prediction technique based on small wavelength short-term memory network |
| CN109376904A (en) * | 2018-09-18 | 2019-02-22 | 广东电网有限责任公司 | A kind of short-term Wind power forecasting method and system based on DWT and LSTM |
| CN109725276A (en) * | 2018-07-25 | 2019-05-07 | 哈尔滨工业大学 | A kind of optical fiber current mutual inductor random error suppressing method based on wavelet analysis |
| CN109816164A (en) * | 2019-01-16 | 2019-05-28 | 国网信通亿力科技有限责任公司 | A kind of Methods of electric load forecasting |
| CN109904878A (en) * | 2019-02-28 | 2019-06-18 | 西安交通大学 | A kind of windy electric field electricity-generating timing simulation scenario building method |
| CN111091233A (en) * | 2019-11-26 | 2020-05-01 | 江苏科技大学 | Wind power plant short-term wind power prediction modeling method based on wavelet analysis and multi-model AdaBoost depth network |
| CN112132360A (en) * | 2020-09-29 | 2020-12-25 | 中交建冀交高速公路投资发展有限公司 | Wind speed short-time confidence interval prediction method and system based on LSTM and GMM |
| CN112598180A (en) * | 2020-12-21 | 2021-04-02 | 北京华能新锐控制技术有限公司 | Distributed regional wind power prediction method |
| CN112613641A (en) * | 2020-12-07 | 2021-04-06 | 河北工业大学 | Short-term electric load combination prediction method based on feature decomposition |
| CN113589253A (en) * | 2021-08-17 | 2021-11-02 | 南昌大学 | Method for detecting weak echo signal based on wavelet transform algorithm of pseudo time domain |
| CN114282711A (en) * | 2021-12-03 | 2022-04-05 | 中国电建集团贵州电力设计研究院有限公司 | Photovoltaic short-term power generation capacity prediction method integrated with time-frequency analysis |
| CN114643904A (en) * | 2022-02-25 | 2022-06-21 | 燕山大学 | Energy management method and device, automobile and storage medium |
-
2023
- 2023-05-22 CN CN202310580416.4A patent/CN116805782A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109725276A (en) * | 2018-07-25 | 2019-05-07 | 哈尔滨工业大学 | A kind of optical fiber current mutual inductor random error suppressing method based on wavelet analysis |
| CN109214566A (en) * | 2018-08-30 | 2019-01-15 | 华北水利水电大学 | Short-term wind power prediction method based on shot and long term memory network |
| CN109214575A (en) * | 2018-09-12 | 2019-01-15 | 河海大学 | A kind of super short-period wind power prediction technique based on small wavelength short-term memory network |
| CN109376904A (en) * | 2018-09-18 | 2019-02-22 | 广东电网有限责任公司 | A kind of short-term Wind power forecasting method and system based on DWT and LSTM |
| CN109816164A (en) * | 2019-01-16 | 2019-05-28 | 国网信通亿力科技有限责任公司 | A kind of Methods of electric load forecasting |
| CN109904878A (en) * | 2019-02-28 | 2019-06-18 | 西安交通大学 | A kind of windy electric field electricity-generating timing simulation scenario building method |
| CN111091233A (en) * | 2019-11-26 | 2020-05-01 | 江苏科技大学 | Wind power plant short-term wind power prediction modeling method based on wavelet analysis and multi-model AdaBoost depth network |
| CN112132360A (en) * | 2020-09-29 | 2020-12-25 | 中交建冀交高速公路投资发展有限公司 | Wind speed short-time confidence interval prediction method and system based on LSTM and GMM |
| CN112613641A (en) * | 2020-12-07 | 2021-04-06 | 河北工业大学 | Short-term electric load combination prediction method based on feature decomposition |
| CN112598180A (en) * | 2020-12-21 | 2021-04-02 | 北京华能新锐控制技术有限公司 | Distributed regional wind power prediction method |
| CN113589253A (en) * | 2021-08-17 | 2021-11-02 | 南昌大学 | Method for detecting weak echo signal based on wavelet transform algorithm of pseudo time domain |
| CN114282711A (en) * | 2021-12-03 | 2022-04-05 | 中国电建集团贵州电力设计研究院有限公司 | Photovoltaic short-term power generation capacity prediction method integrated with time-frequency analysis |
| CN114643904A (en) * | 2022-02-25 | 2022-06-21 | 燕山大学 | Energy management method and device, automobile and storage medium |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117424290A (en) * | 2023-10-07 | 2024-01-19 | 国家电网有限公司华东分部 | New energy source inclusion proportion calculating method, device, equipment and storage medium |
| CN117424290B (en) * | 2023-10-07 | 2024-04-19 | 国家电网有限公司华东分部 | New energy source inclusion proportion calculating method, device, equipment and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huang et al. | Forecasting hourly solar irradiance using hybrid wavelet transformation and Elman model in smart grid | |
| CN110941928B (en) | Rolling bearing residual life prediction method based on dropout-SAE and Bi-LSTM | |
| CN111242377B (en) | Short-term wind speed prediction method integrating deep learning and data denoising | |
| Lin et al. | Wide‐area coherency identification of generators in interconnected power systems with renewables | |
| CN112434848B (en) | Nonlinear weighted combination wind power prediction method based on deep belief network | |
| CN112100911B (en) | Solar radiation prediction method based on depth BILSTM | |
| Zhang et al. | LightGBM‐based model for metro passenger volume forecasting | |
| CN116805782A (en) | New energy output scene generation method and device and computer equipment | |
| Perpiñán et al. | Analysis and synthesis of the variability of irradiance and PV power time series with the wavelet transform | |
| Toms et al. | Testing the reliability of interpretable neural networks in geoscience using the Madden–Julian oscillation | |
| CN116169670A (en) | Short-term non-resident load prediction method and system based on improved neural network | |
| Peng et al. | Electric load forecasting based on wavelet transform and random forest | |
| Li et al. | Two-stage hybrid deep learning with strong adaptability for detailed day-ahead photovoltaic power forecasting | |
| Kim et al. | Tutorial on time series prediction using 1D-CNN and BiLSTM: A case example of peak electricity demand and system marginal price prediction | |
| Fawzy et al. | Trio-V wind analyzer: a generic integral system for wind farm suitability design and power prediction using big data analytics | |
| Karozis et al. | A deep learning approach for spatial error correction of numerical seasonal weather prediction simulation data | |
| CN115619999A (en) | Real-time monitoring method and device for power equipment, electronic equipment and readable medium | |
| CN117292143A (en) | Searching method, system and device based on deep learning of massive sun observation images | |
| CN116565863A (en) | Short-term photovoltaic output prediction method based on space-time correlation | |
| CN116739172A (en) | Method and device for ultra-short-term prediction of offshore wind power based on climbing identification | |
| Mahinthakumar et al. | Reconstructing groundwater source release histories using hybrid optimization approaches | |
| Gupta et al. | Day‐ahead and intra‐day wind power forecasting based on feedback error correction | |
| MANUSOV et al. | Analysis of electricity consumption forecasting methods for the coal industry. | |
| Ding et al. | A mixed simulation methodology for long-term wind power with 4D fluctuation features clustering method and asymmetric fluctuations | |
| CN117151303B (en) | Ultra-short-term solar irradiance prediction method and system based on hybrid model |
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 |