CN113779861A - Photovoltaic power prediction method and terminal equipment - Google Patents
Photovoltaic power prediction method and terminal equipment Download PDFInfo
- Publication number
- CN113779861A CN113779861A CN202110836483.9A CN202110836483A CN113779861A CN 113779861 A CN113779861 A CN 113779861A CN 202110836483 A CN202110836483 A CN 202110836483A CN 113779861 A CN113779861 A CN 113779861A
- Authority
- CN
- China
- Prior art keywords
- photovoltaic
- frequency
- prediction
- power
- data
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 56
- 238000000354 decomposition reaction Methods 0.000 claims description 32
- 238000012549 training Methods 0.000 claims description 25
- 238000004590 computer program Methods 0.000 claims description 19
- 230000035772 mutation Effects 0.000 claims description 17
- 230000008859 change Effects 0.000 claims description 5
- 230000006870 function Effects 0.000 description 14
- 238000003062 neural network model Methods 0.000 description 11
- 230000008569 process Effects 0.000 description 11
- 238000013528 artificial neural network Methods 0.000 description 8
- 238000012545 processing Methods 0.000 description 6
- 238000011161 development Methods 0.000 description 5
- 238000010586 diagram Methods 0.000 description 5
- 238000005516 engineering process Methods 0.000 description 5
- 230000007613 environmental effect Effects 0.000 description 5
- 238000010248 power generation Methods 0.000 description 5
- 239000011159 matrix material Substances 0.000 description 4
- 238000004422 calculation algorithm Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 238000013461 design Methods 0.000 description 3
- 238000004364 calculation method Methods 0.000 description 2
- 238000004891 communication Methods 0.000 description 2
- 238000003912 environmental pollution Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 230000004913 activation Effects 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 230000003416 augmentation Effects 0.000 description 1
- 230000003190 augmentative effect Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000011478 gradient descent method Methods 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 238000005457 optimization Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/06—Energy or water supply
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y04—INFORMATION OR COMMUNICATION TECHNOLOGIES HAVING AN IMPACT ON OTHER TECHNOLOGY AREAS
- Y04S—SYSTEMS INTEGRATING TECHNOLOGIES RELATED TO POWER NETWORK OPERATION, COMMUNICATION OR INFORMATION TECHNOLOGIES FOR IMPROVING THE ELECTRICAL POWER GENERATION, TRANSMISSION, DISTRIBUTION, MANAGEMENT OR USAGE, i.e. SMART GRIDS
- Y04S10/00—Systems supporting electrical power generation, transmission or distribution
- Y04S10/50—Systems or methods supporting the power network operation or management, involving a certain degree of interaction with the load-side end user applications
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Evolutionary Computation (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- Public Health (AREA)
- Development Economics (AREA)
- Primary Health Care (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Medical Informatics (AREA)
- Computer Hardware Design (AREA)
- Geometry (AREA)
- Water Supply & Treatment (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Supply And Distribution Of Alternating Current (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention is suitable for the technical field of photovoltaic, and provides a photovoltaic power prediction method and terminal equipment, wherein the method comprises the following steps: acquiring current meteorological data; inputting current meteorological data into the power component prediction model aiming at each power component prediction model in a first preset number of pre-trained power component prediction models to obtain a high-frequency prediction component and a low-frequency prediction component corresponding to the power component prediction model; reconstructing the high-frequency prediction components of the first preset number to obtain a high-frequency photovoltaic power prediction value; reconstructing the low-frequency prediction components of a first preset number to obtain a low-frequency photovoltaic power prediction value; according to the photovoltaic power prediction method, a plurality of models are adopted for fine prediction, and a plurality of low-frequency prediction components and a plurality of high-frequency prediction components obtained through prediction are reconstructed to obtain the photovoltaic power prediction value, so that the overall prediction precision is higher.
Description
Technical Field
The invention belongs to the technical field of photovoltaic, and particularly relates to a photovoltaic power prediction method and terminal equipment.
Background
The utilization of renewable energy is one of important ways to solve the problems of global energy scarcity and environmental pollution, and photovoltaic power generation is the means with the development prospect and convenience in new energy development at present. Because the photovoltaic power generation power is influenced by meteorological factors, and the process of converting light energy into electric energy by the photovoltaic module is influenced by the equipment, the photovoltaic output has strong randomness and fluctuation. With the continuous increase of grid-connected capacity, the randomness and the volatility of photovoltaic output bring great threat to the safe and stable operation of a power grid, so that the accurate prediction of the photovoltaic output has great significance for improving the safe and stable operation of the power grid.
In the prior art, a neural network model is generally adopted to predict photovoltaic power, a prediction model of various environmental conditions influencing photovoltaic output is firstly established, environmental data is predicted, and then secondary modeling is carried out to predict photovoltaic output. The method needs two modeling predictions, and the error of the first prediction can be amplified in the second prediction, so that the accuracy of the prediction result is low
Disclosure of Invention
In view of this, the embodiment of the invention provides a photovoltaic power prediction method and terminal equipment, so as to solve the problem that in the prior art, the prediction accuracy is low when a neural network model is adopted to predict a photovoltaic power prediction result through secondary modeling.
A first aspect of an embodiment of the present invention provides a method for predicting photovoltaic power, including:
acquiring current meteorological data;
inputting current meteorological data into the power component prediction model aiming at each power component prediction model in a first preset number of pre-trained power component prediction models to obtain a high-frequency prediction component and a low-frequency prediction component corresponding to the power component prediction model;
reconstructing the high-frequency prediction components of the first preset number to obtain a high-frequency photovoltaic power prediction value; reconstructing the low-frequency prediction components of a first preset number to obtain a low-frequency photovoltaic power prediction value; wherein the photovoltaic power prediction value comprises: the high-frequency photovoltaic power prediction value and the low-frequency photovoltaic power prediction value.
A second aspect of the embodiments of the present invention provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method for predicting photovoltaic power provided by the first aspect of the embodiments of the present invention when executing the computer program.
A third aspect of embodiments of the present invention provides a computer-readable storage medium, in which a computer program is stored, and the computer program, when executed by a processor, implements the steps of the method for predicting photovoltaic power provided by the first aspect of embodiments of the present invention.
The embodiment of the invention provides a photovoltaic power prediction method and terminal equipment, wherein the method comprises the following steps: acquiring current meteorological data; inputting current meteorological data into the power component prediction model aiming at each power component prediction model in a first preset number of pre-trained power component prediction models to obtain a high-frequency prediction component and a low-frequency prediction component corresponding to the power component prediction model; reconstructing the high-frequency prediction components of the first preset number to obtain a high-frequency photovoltaic power prediction value; reconstructing the low-frequency prediction components of a first preset number to obtain a low-frequency photovoltaic power prediction value; according to the embodiment of the invention, a plurality of models are adopted for fine prediction, and a plurality of low-frequency prediction components and a plurality of high-frequency prediction components obtained through prediction are reconstructed to obtain the photovoltaic power prediction value, so that the overall prediction precision is higher.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present invention, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without inventive exercise.
Fig. 1 is a schematic implementation flow diagram of a photovoltaic power prediction method according to an embodiment of the present invention;
FIG. 2 is a schematic diagram of a power component prediction model in a neural network model according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of a photovoltaic power prediction apparatus provided by an embodiment of the present invention;
fig. 4 is a schematic diagram of a terminal device according to an embodiment of the present invention.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the invention. It will be apparent, however, to one skilled in the art that the present invention may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.
In order to explain the technical means of the present invention, the following description will be given by way of specific examples.
The utilization of renewable energy is one of the important ways to solve the problems of global energy scarcity and environmental pollution, so the development of new energy has attracted global attention. Among them, photovoltaic power generation is the means having the development prospect and convenience condition in the development of new energy at present. Because the photovoltaic power generation power is influenced by meteorological factors, and the process of converting light energy into electric energy by a photovoltaic module is influenced by equipment, the photovoltaic output has strong randomness and fluctuation finally, and the output change is an uncertain process. With the continuous increase of grid-connected capacity, the randomness and the volatility of photovoltaic output bring great threats to the safe and stable operation of a power grid, so that the method has important significance for the accurate prediction of the photovoltaic output. (1) The operation and control of the whole prediction system can be optimized through accurate photovoltaic output prediction, a more scientific and reasonable scheduling strategy can be conveniently formulated, negative effects of the photovoltaic system on a large power grid after grid connection can be reduced, and the safety and stability of the power system are improved. (2) The photovoltaic power prediction is matched with scheduling, so that the consumption level of new energy can be improved, other power generation modes are coordinated, and the energy is saved.
In the prior art, a neural network model is generally adopted to predict photovoltaic power, a prediction model of various environmental conditions influencing photovoltaic output is firstly established, environmental data is predicted, and then secondary modeling is carried out to predict photovoltaic output. The method needs two modeling predictions, and the error of the first prediction can be amplified in the second prediction, so that the accuracy of the prediction result is low
Based on the above, referring to fig. 1, an embodiment of the present invention provides a method for predicting photovoltaic power, including:
s101: acquiring current meteorological data;
s102: inputting current meteorological data into the power component prediction model aiming at each power component prediction model in a first preset number of pre-trained power component prediction models to obtain a high-frequency prediction component and a low-frequency prediction component corresponding to the power component prediction model;
s103: reconstructing the high-frequency prediction components of the first preset number to obtain a high-frequency photovoltaic power prediction value; reconstructing the low-frequency prediction components of a first preset number to obtain a low-frequency photovoltaic power prediction value; wherein the photovoltaic power prediction value comprises: the high-frequency photovoltaic power prediction value and the low-frequency photovoltaic power prediction value.
In the embodiment of the invention, the influence of the basic (high-frequency) component on the photovoltaic output is considered, and the influence of the random fluctuation (low-frequency) component on the output is also considered, so that the combined prediction precision is higher. Meanwhile, local microscopic characteristics of a decomposition technology are utilized to predict each component respectively to obtain a plurality of high-frequency prediction components and a plurality of low-frequency prediction components, then the plurality of high-frequency prediction components are superposed and reconstructed, data are restored to the maximum extent to obtain high-frequency photovoltaic power prediction values, and the plurality of low-frequency prediction components are reconstructed to obtain low-frequency photovoltaic power prediction values. The embodiment of the invention adopts combined prediction and simultaneously predicts the photovoltaic treatment by utilizing the local microscopic characteristic of the decomposition technology, so that the overall prediction precision is higher.
In some embodiments, before S102, the method may further include:
s104: acquiring historical photovoltaic data; wherein the photovoltaic data comprises: meteorological data and photovoltaic power data;
s105: establishing a first preset number of basic prediction models;
s106: and training each basic prediction model according to historical photovoltaic data to obtain a first preset number of power component prediction models which are trained in advance.
In some embodiments, the meteorological data may include: the maximum air temperature, the minimum air temperature, the relative humidity, the air density, the atmospheric pressure, the weather type and other environmental factors influencing the photovoltaic output.
In some embodiments, S106 may include:
s1061: decomposing photovoltaic power data in the photovoltaic data aiming at each photovoltaic data in the historical photovoltaic data to obtain a high-frequency power sequence component and a low-frequency power sequence component corresponding to the photovoltaic data; carrying out variation modal decomposition on high-frequency power sequence components corresponding to the photovoltaic data to obtain a first preset number of high-frequency components; carrying out variation modal decomposition on low-frequency power sequence components corresponding to the photovoltaic data to obtain a first preset number of low-frequency components; meteorological data, a kth-order high-frequency component and a kth-order low-frequency component corresponding to the photovoltaic data form a training sample of a kth basic prediction model;
s1062: training the kth basic prediction model by adopting a training sample of the kth basic prediction model corresponding to each photovoltaic data to obtain a kth pre-trained power component prediction model; where K is 1,2, …, K being a first predetermined number.
In some embodiments, the base predictive model may be a neural network model.
The method adopts a basic prediction model to learn the mapping relation between meteorological data and each order of modal components to obtain each power component prediction model (one modal component corresponds to one power component prediction model). The neural network model is combined with the variational modal decomposition technology, the characteristics are highlighted, and the prediction precision is high.
The sunlight volt power curve and the corresponding meteorological data are one piece of data. The first preset number is 10, the historical photovoltaic data is data of the previous 30 days, and then 30 x 10 training samples are obtained by decomposing the photovoltaic power data of each day. 30 1-order training samples (meteorological data, 1-order high-frequency components and 1-order low-frequency components) for training a 1 st basic prediction model to obtain a 1 st power component prediction model; the same way can be used to obtain the remaining 9 component prediction models. Further, inputting meteorological data of a day to be predicted into the first power component prediction model to obtain a 1-order high-frequency component and a 1-order high-frequency component of the day to be predicted; the same way can get the remaining 9 high frequency components and 9 low frequency components. And reconstructing the 10 high-frequency components to obtain a high-frequency photovoltaic power predicted value of the day to be predicted, and reconstructing the 10 low-frequency components to obtain a low-frequency photovoltaic power predicted value of the day to be predicted.
In some embodiments, the base prediction model may be an RBF neural network model.
The general prediction model mostly adopts a BP neural network, but the BP neural network has the following disadvantages: the BP neural network algorithm adopts a gradient descent method to optimize network parameters, the learning rate is fixed, when a complex problem is processed, the efficiency is low, and the training result is probably locally optimal. The hidden layer design of the BP neural network has no mature theoretical basis, so the hidden layer design can only be pieced together according to the experience of designers.
Compared with a BP neural network, the RBF neural network has a simple structure, high training speed and strong generalization capability due to the change of the learning rate, has nonlinear fitting capability comparable to that of the BP neural network, can avoid falling into local optimization, and has higher prediction precision, so that the basic prediction model in the embodiment of the invention adopts an RBF neural network model.
And continuously adjusting the number of nodes of the hidden layer by a trial and error method in the training process of the RBF neural network model to obtain the network structure. The activation function of the network is selected as follows: the nonlinear function is adjusted by adopting a Gaussian function, and as long as the nodes of the hidden layer are enough, the RBF neural network model can simulate any nonlinear mapping relation. The gaussian function expression is:
wherein X is an input vector, and X is (X)1,x2…,xn)TThe dimension is determined by the number of main factors having influence on the pre-measurement; ci＝(c1,c2…,cn)TThe central vector of the Gaussian function of the ith hidden layer is the same as the dimension of the input vector; sigmaiIs the scale parameter of the ith hidden layer Gaussian function.
The output layer and the hidden layer are connected through a weight vector, the final output is determined by continuously adjusting the weight vector, and the output expression of the RBF neural network is as follows:
the training steps are as follows:
1) input training sample X ═ X1、x2…xnCalculating power output value Y through sample matrix and weight matrix W1、Y2，Y1＝f1(W1,X),Y2＝f2(W2X), wherein f1、f2Is a non-linear function;
2) respectively calculating predicted values Y by adopting cost functions1、Y2And true value
Error L between1、L2，
3) Calculating and updating the weight matrix according to the error obtained by current calculation and the current weight matrix,
and finishing training by the network until the error meets the requirement or the maximum iteration number is reached.
The process of predicting by using the trained RBF neural network model is shown in FIG. 2.
In some embodiments, decomposing the photovoltaic power data in the photovoltaic data to obtain a high-frequency power sequence component and a low-frequency power sequence component corresponding to the photovoltaic data may include:
and sampling photovoltaic power data in the photovoltaic data, and obtaining a high-frequency power sequence component and a low-frequency power sequence component corresponding to the photovoltaic data through discrete wavelet decomposition.
In some embodiments, each of the historical photovoltaic data has similar meteorological features.
Similar day data can be selected from more historical operating data by adopting a grey correlation degree analysis method to serve as historical photovoltaic data. Specifically, the data with the similarity larger than the threshold value is selected to form historical photovoltaic data.
The similarity calculation formula is as follows:
wherein, X0For a weather condition of a day to be predicted, XjIndicating a weather condition, σ, on a similar dayjRepresenting the correlation coefficient, ηjAnd expressing the similarity, wherein rho is a resolution coefficient and is generally 0.5.
For example, the model is trained by using historical photovoltaic data of a sunny day, and the power component prediction model is only used for predicting photovoltaic power of the sunny day. The model training difficulty is small, and the prediction precision is relatively high.
In some embodiments, before S105, the method may further include:
s107: a first preset number of values is determined from historical photovoltaic data.
In some embodiments, S107 may include:
s1071: determining the number of first components corresponding to the high-frequency components and the number of second components corresponding to the low-frequency components through singular value decomposition according to historical photovoltaic data;
s1072: and taking the larger value of the first component number and the second component number as the value of the first preset number.
The method comprises the following specific steps of variational modal decomposition:
1. constructing variation problem, assuming that data f (t) is decomposed into k components, in order to ensure that the decomposition sequence is a modal component with limited bandwidth of the center frequency, and to ensure that the sum of the estimated broadband of each modal component is minimum, the constraint condition is that the sum of all modal components is equal to f (t). Then the variational expression with the constraint is:
wherein K is the number of modal components of the final decomposition, uk、ωkThe k-th modal component and its center frequency, respectively, δ (t) is the dirac function, and is the sign of the convolution operation.
2. Solving the above formula, introducing a Lagrange multiplier lambda and constructing a Lagrange function, converting the variational problem with the constraint into an unconstrained variational problem, and obtaining an augmentation expression as follows:
wherein, alpha is a secondary penalty factor and is used for reducing the interference of Gaussian noise. Optimizing to obtain each modal component and center frequency by using an alternating direction multiplier iterative algorithm in combination with the Pasteval theorem and Fourier equidistant transformation, searching saddle points of the augmented Lagrange function, and alternately optimizing the u after iterationk、ωkThe expression of (a) is:
wherein the content of the first and second substances,
are f (t), u respectivelyk(t), Fourier transform of λ (t), ω denotes frequency, and n denotes number of iterations.
The variational modal decomposition technology is a new modal decomposition method different from a recursive mode, has excellent frequency decomposition characteristics, but is seriously influenced by the number of components (namely a first preset number) when processing signals, the number of the components is difficult to reasonably set through subjective experience, and modal aliasing phenomenon can be caused when the number of the components is not set reasonably.
According to the singular value decomposition principle, the denoising process is to reserve the first K large singular values, zero the singular values after K, and the reconstructed sequence can basically and accurately reflect the original sequence. From the construction principle, the first K large singular values reflect the main components of the sequence, the smaller singular values after K reflect the noise components, the K value can be determined according to the singular value distribution curve, and when the singular value is rapidly reduced from the maximum value to the stable minimum value, the turning point is the singular value order K value. Whereas the variational modal decomposition is directly removed when processing the noise part. Therefore, the catastrophe point K value after singular value decomposition and the component number K of variation modal decomposition play the same role in the sequence processing process, so the modal component number K can be determined according to the effective order of singular value decomposition.
In the embodiment of the invention, the value of the first preset quantity can be determined by adopting a singular value decomposition technology according to historical data, the value of the first preset quantity is dynamically determined according to different meteorological environments, and different weather environments correspond to different numerical values, so that the scheme is suitable for different meteorological environments, and meanwhile, a larger value is selected as the value of the first preset quantity according to high-frequency components and low-frequency components.
In some embodiments, the historical photovoltaic data is photovoltaic data under the same meteorological conditions; s1071 may include:
1. selecting one photovoltaic data from the historical photovoltaic data as target photovoltaic data;
2. decomposing the target photovoltaic data to obtain a high-frequency power sequence component and a low-frequency power sequence component corresponding to the target photovoltaic data;
3. singular value decomposition is carried out on high-frequency power sequence components corresponding to the target photovoltaic data, and a first singular value distribution curve is obtained; singular value decomposition is carried out on the low-frequency power sequence component corresponding to the target photovoltaic data, and a second singular value distribution curve is obtained;
4. searching singular value mutation points in the first singular value distribution curve, and taking orders corresponding to the singular value mutation points in the first singular value distribution curve as a first component number; and searching singular value mutation points in the second singular value distribution curve, and taking the order corresponding to the singular value mutation points in the second singular value distribution curve as the second component number.
Examples of the invention
In some embodiments, the singular value discontinuities may satisfy the following condition:
dkm＝km+1-km>thrmax
dkm+1＝km+2-km+1<thrmin
wherein m is the order corresponding to the singular value mutation point, kmSlope at singular value break, dkmThe change amount of the slope at the singular value mutation point.
Wherein, thrmaxCan be 50, thrminThe number of the grooves can be 5, and the grooves can also be set according to the actual application requirements.
In some embodiments, the method may further include:
s108: and correcting the photovoltaic power predicted value by adopting the low-frequency photovoltaic power predicted value to obtain the corrected photovoltaic power predicted value.
In the embodiment of the invention, the high-frequency photovoltaic power predicted value (basic photovoltaic power predicted value) obtained by prediction can be used for day-ahead optimized scheduling, and the low-frequency photovoltaic power predicted value (randomly shifted photovoltaic power predicted value) can be used for correcting the photovoltaic power predicted value, so that the accuracy of the photovoltaic power predicted value is further improved. The specific correction method is not described herein.
It should be understood that, the sequence numbers of the steps in the foregoing embodiments do not imply an execution sequence, and the execution sequence of each process should be determined by its function and inherent logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention.
Referring to fig. 3, an embodiment of the present invention provides a photovoltaic power prediction apparatus, including:
a first parameter obtaining module 21, configured to obtain current meteorological data;
the model prediction module 22 is configured to input current meteorological data into each power component prediction model of a first preset number of pre-trained power component prediction models to obtain a high-frequency prediction component and a low-frequency prediction component corresponding to the power component prediction model;
the reconstruction module 23 is configured to reconstruct the high-frequency prediction components of the first preset number to obtain a high-frequency photovoltaic power prediction value; reconstructing the low-frequency prediction components of a first preset number to obtain a low-frequency photovoltaic power prediction value; wherein the photovoltaic power prediction value comprises: the high-frequency photovoltaic power prediction value and the low-frequency photovoltaic power prediction value.
In some embodiments, the apparatus may further include:
the second parameter acquisition module 24 is used for acquiring historical photovoltaic data; wherein the photovoltaic data comprises: meteorological data and photovoltaic power data;
a model building module 25, configured to build a first preset number of basic prediction models;
and the model training module 26 is configured to train each basic prediction model according to the historical photovoltaic data to obtain a first preset number of power component prediction models which are trained in advance.
In some embodiments, model training module 26 may include:
the training sample generation unit 261 is configured to decompose, for each photovoltaic data in the historical photovoltaic data, the photovoltaic power data in the photovoltaic data to obtain a high-frequency power sequence component and a low-frequency power sequence component corresponding to the photovoltaic data; carrying out variation modal decomposition on high-frequency power sequence components corresponding to the photovoltaic data to obtain a first preset number of high-frequency components; carrying out variation modal decomposition on low-frequency power sequence components corresponding to the photovoltaic data to obtain a first preset number of low-frequency components; meteorological data, a kth-order high-frequency component and a kth-order low-frequency component corresponding to the photovoltaic data form a training sample of a kth basic prediction model;
the training unit 262 is configured to train the kth basic prediction model by using a training sample of the kth basic prediction model corresponding to each photovoltaic data, so as to obtain a kth power component prediction model trained in advance; where K is 1,2, …, K being a first predetermined number.
In some embodiments, the apparatus may further include:
a parameter determining module 27, configured to determine a value of the first preset number according to the historical photovoltaic data.
In some embodiments, the parameter determination module 27 may include:
an initial value determining unit 271, configured to determine, according to the historical photovoltaic data, the number of first components corresponding to the high-frequency component and the number of second components corresponding to the low-frequency component by singular value decomposition;
a comparing unit 272, configured to use a larger value of the first component number and the second component number as a value of the first preset number.
In some embodiments, the historical photovoltaic data is photovoltaic data under the same meteorological conditions; the initial value determining unit 271 is specifically configured to:
1. selecting one photovoltaic data from the historical photovoltaic data as target photovoltaic data;
2. decomposing the target photovoltaic data to obtain a high-frequency power sequence component and a low-frequency power sequence component corresponding to the target photovoltaic data;
3. singular value decomposition is carried out on high-frequency power sequence components corresponding to the target photovoltaic data, and a first singular value distribution curve is obtained; singular value decomposition is carried out on the low-frequency power sequence component corresponding to the target photovoltaic data, and a second singular value distribution curve is obtained;
4. searching singular value mutation points in the first singular value distribution curve, and taking orders corresponding to the singular value mutation points in the first singular value distribution curve as a first component number; and searching singular value mutation points in the second singular value distribution curve, and taking the order corresponding to the singular value mutation points in the second singular value distribution curve as the second component number.
In some embodiments, the singular value discontinuities may satisfy the following condition:
dkm＝km+1-km>thrmax
dkm+1＝km+2-km+1<thrmin
wherein m isOrder, k, corresponding to singular value break pointsmSlope at singular value break, dkmThe change amount of the slope at the singular value mutation point.
In some embodiments, the apparatus may further include:
and the correcting module 28 is configured to correct the photovoltaic power predicted value by using the low-frequency photovoltaic power predicted value to obtain a corrected photovoltaic power predicted value.
It is obvious to those skilled in the art that, for convenience and simplicity of description, the foregoing division of the functional units and modules is merely used as an example, and in practical applications, the above function distribution may be performed by different functional units and modules as needed, that is, the internal structure of the terminal device is divided into different functional units or modules to perform all or part of the above described functions. Each functional unit and module in the embodiments may be integrated in one processing unit, or each unit may exist alone physically, or two or more units are integrated in one unit, and the integrated unit may be implemented in a form of hardware, or in a form of software functional unit. In addition, specific names of the functional units and modules are only for convenience of distinguishing from each other, and are not used for limiting the protection scope of the present application. The specific working processes of the units and modules in the above-mentioned apparatus may refer to the corresponding processes in the foregoing method embodiments, and are not described herein again.
Fig. 4 is a schematic block diagram of a terminal device according to an embodiment of the present invention. As shown in fig. 4, the terminal device 4 of this embodiment includes: one or more processors 40, a memory 41, and a computer program 42 stored in the memory 41 and executable on the processors 40. The processor 40, when executing the computer program 42, implements the steps in the above-described respective embodiments of the method for predicting photovoltaic power, such as the steps S101 to S103 shown in fig. 1. Alternatively, the processor 40, when executing the computer program 42, implements the functionality of the modules/units in the above-described embodiment of the apparatus for predicting photovoltaic power, such as the functionality of the modules 21 to 23 shown in fig. 3.
Illustratively, the computer program 42 may be divided into one or more modules/units, which are stored in the memory 41 and executed by the processor 40 to accomplish the present application. One or more of the modules/units may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 42 in the terminal device 4. For example, the computer program 42 may be partitioned into the first parameter acquisition module 21, the model prediction module 22, and the reconstruction module 23.
A first parameter obtaining module 21, configured to obtain current meteorological data;
the model prediction module 22 is configured to input current meteorological data into each power component prediction model of a first preset number of pre-trained power component prediction models to obtain a high-frequency prediction component and a low-frequency prediction component corresponding to the power component prediction model;
the reconstruction module 23 is configured to reconstruct the high-frequency prediction components of the first preset number to obtain a high-frequency photovoltaic power prediction value; reconstructing the low-frequency prediction components of a first preset number to obtain a low-frequency photovoltaic power prediction value; wherein the photovoltaic power prediction value comprises: the high-frequency photovoltaic power prediction value and the low-frequency photovoltaic power prediction value.
Other modules or units are not described in detail herein.
The Processor 40 may be a Central Processing Unit (CPU), other general purpose Processor, a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, discrete Gate or transistor logic device, discrete hardware component, etc. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 41 may be an internal storage unit of the terminal device, such as a hard disk or a memory of the terminal device. The memory 41 may also be an external storage device of the terminal device, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the terminal device. Further, the memory 41 may also include both an internal storage unit of the terminal device and an external storage device. The memory 41 is used for storing the computer program 42 and other programs and data required by the terminal device. The memory 41 may also be used to temporarily store data that has been output or is to be output.
In the above embodiments, the descriptions of the respective embodiments have respective emphasis, and reference may be made to the related descriptions of other embodiments for parts that are not described or illustrated in a certain embodiment.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present application.
In the embodiments provided in the present application, it should be understood that the disclosed terminal device and method may be implemented in other ways. For example, the above-described terminal device embodiments are merely illustrative, and for example, a module or a unit may be divided into only one logical function, and may be implemented in other ways, for example, multiple units or components may be combined or integrated into another system, or some features may be omitted or not executed. In addition, the shown or discussed mutual coupling or direct coupling or communication connection may be an indirect coupling or communication connection through some interfaces, devices or units, and may be in an electrical, mechanical or other form.
Units described as separate parts may or may not be physically separate, and parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of the embodiment.
In addition, functional units in the embodiments of the present application may be integrated into one processing unit, or each unit may exist alone physically, or two or more units are integrated into one unit. The integrated unit can be realized in a form of hardware, and can also be realized in a form of a software functional unit.
The integrated modules/units, if implemented in the form of software functional units and sold or used as separate products, may be stored in a computer readable storage medium. Based on such understanding, all or part of the flow in the method according to the embodiments described above may be implemented by a computer program, which is stored in a computer readable storage medium and used by a processor to implement the steps of the embodiments of the methods described above. Wherein the computer program comprises computer program code, which may be in the form of source code, object code, an executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying computer program code, recording medium, usb disk, removable hard disk, magnetic disk, optical disk, computer Memory, Read-Only Memory (ROM), Random Access Memory (RAM), electrical carrier wave signals, telecommunications signals, software distribution medium, and the like. It should be noted that the computer readable medium may include any suitable increase or decrease as required by legislation and patent practice in the jurisdiction, for example, in some jurisdictions, computer readable media may not include electrical carrier signals and telecommunications signals in accordance with legislation and patent practice.
The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. A method for predicting photovoltaic power, comprising:
acquiring current meteorological data;
inputting the current meteorological data into the power component prediction model aiming at each power component prediction model in a first preset number of pre-trained power component prediction models to obtain a high-frequency prediction component and a low-frequency prediction component corresponding to the power component prediction model;
reconstructing the first preset number of high-frequency prediction components to obtain a high-frequency photovoltaic power prediction value; reconstructing the first preset number of low-frequency prediction components to obtain a low-frequency photovoltaic power prediction value; wherein the photovoltaic power prediction value comprises: the high-frequency photovoltaic power prediction value and the low-frequency photovoltaic power prediction value.
2. The method of predicting photovoltaic power as claimed in claim 1, wherein before inputting the current meteorological data into the power component prediction model for each of the first predetermined number of pre-trained power component prediction models to obtain the high-frequency prediction component and the low-frequency prediction component corresponding to the power component prediction model, the method further comprises:
acquiring historical photovoltaic data; wherein the photovoltaic data comprises: meteorological data and photovoltaic power data;
establishing a first preset number of basic prediction models;
and training each basic prediction model according to the historical photovoltaic data to obtain a first preset number of power component prediction models which are trained in advance.
3. The method for predicting photovoltaic power according to claim 2, wherein the training of each basic prediction model according to the historical photovoltaic data to obtain the first preset number of power component prediction models trained in advance comprises:
decomposing photovoltaic power data in the photovoltaic data aiming at each photovoltaic data in the historical photovoltaic data to obtain a high-frequency power sequence component and a low-frequency power sequence component corresponding to the photovoltaic data; carrying out variation modal decomposition on high-frequency power sequence components corresponding to the photovoltaic data to obtain a first preset number of high-frequency components; carrying out variation modal decomposition on low-frequency power sequence components corresponding to the photovoltaic data to obtain a first preset number of low-frequency components; meteorological data, a kth-order high-frequency component and a kth-order low-frequency component corresponding to the photovoltaic data form a training sample of a kth basic prediction model;
training the kth basic prediction model by adopting a training sample of the kth basic prediction model corresponding to each photovoltaic data to obtain a kth pre-trained power component prediction model; where K is 1,2, …, K being the first predetermined number.
4. The method for predicting photovoltaic power as recited in claim 3, wherein before said establishing a first preset number of basic predictive models, said method further comprises:
and determining the value of the first preset quantity according to the historical photovoltaic data.
5. The method for predicting photovoltaic power as claimed in claim 4, wherein said determining the value of the first preset number from the historical photovoltaic data comprises:
determining the number of first components corresponding to the high-frequency components and the number of second components corresponding to the low-frequency components through singular value decomposition according to the historical photovoltaic data;
and taking the larger value of the first component number and the second component number as the value of the first preset number.
6. The method for predicting photovoltaic power according to claim 5, wherein the historical photovoltaic data is photovoltaic data under the same meteorological condition; determining the number of first components corresponding to the high-frequency components and the number of second components corresponding to the low-frequency components through singular value decomposition according to the historical photovoltaic data, wherein the determining comprises the following steps:
selecting one photovoltaic data from the historical photovoltaic data as target photovoltaic data;
decomposing the target photovoltaic data to obtain a high-frequency power sequence component and a low-frequency power sequence component corresponding to the target photovoltaic data;
singular value decomposition is carried out on the high-frequency power sequence component corresponding to the target photovoltaic data, and a first singular value distribution curve is obtained; singular value decomposition is carried out on the low-frequency power sequence component corresponding to the target photovoltaic data, and a second singular value distribution curve is obtained;
searching singular value mutation points in the first singular value distribution curve, and taking orders corresponding to the singular value mutation points in the first singular value distribution curve as the first component number; and searching singular value mutation points in the second singular value distribution curve, and taking orders corresponding to the singular value mutation points in the second singular value distribution curve as the second component number.
7. The method for predicting photovoltaic power as claimed in claim 6, wherein the singular value discontinuity point satisfies the following condition:
dkm＝km+1-km>thrmax
dkm+1＝km+2-km+1<thrmin
wherein m is the order corresponding to the singular value mutation point, kmAs the slope at the singular value break point, dkmThe change amount of the slope at the singular value mutation point is shown.
8. The method for predicting photovoltaic power as claimed in any one of claims 1 to 7, wherein the method further comprises:
and correcting the photovoltaic power predicted value by adopting the low-frequency photovoltaic power predicted value to obtain a corrected photovoltaic power predicted value.
9. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the steps of the method for predicting photovoltaic power according to any one of claims 1 to 8 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method for predicting photovoltaic power according to any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110836483.9A CN113779861B (en) | 2021-07-23 | 2021-07-23 | Photovoltaic Power Prediction Method and Terminal Equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110836483.9A CN113779861B (en) | 2021-07-23 | 2021-07-23 | Photovoltaic Power Prediction Method and Terminal Equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113779861A true CN113779861A (en) | 2021-12-10 |
| CN113779861B CN113779861B (en) | 2023-08-22 |
Family
ID=78836216
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110836483.9A Active CN113779861B (en) | 2021-07-23 | 2021-07-23 | Photovoltaic Power Prediction Method and Terminal Equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113779861B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117076933A (en) * | 2023-10-16 | 2023-11-17 | 锦浪科技股份有限公司 | Training of arc judgment model, photovoltaic direct current arc detection method and computing equipment |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927593A (en) * | 2014-04-22 | 2014-07-16 | 国家电网公司 | Photovoltaic generation power prediction method based on self-learning composite data source autoregression model |
| CN106446494A (en) * | 2016-05-11 | 2017-02-22 | 新疆大学 | Wavelet packet-neural network-based wind/photovoltaic power prediction method |
| CN106503851A (en) * | 2016-10-25 | 2017-03-15 | 国家电网公司 | A kind of improved Short-Term Load Forecasting Method based on wavelet analysises |
| CN106815659A (en) * | 2017-01-20 | 2017-06-09 | 国网浙江省电力公司电力科学研究院 | A kind of ultra-short term forecast of solar irradiance method and its device based on mixed model |
| CN107194496A (en) * | 2017-04-25 | 2017-09-22 | 甘肃省电力公司风电技术中心 | The Forecasting Methodology and prediction meanss of photovoltaic power |
| CN107563565A (en) * | 2017-09-14 | 2018-01-09 | 广西大学 | A kind of short-term photovoltaic for considering Meteorology Factor Change decomposes Forecasting Methodology |
| US20180240200A1 (en) * | 2015-09-30 | 2018-08-23 | China Electric Power Research Institute Company Limited | Method and device for modeling a long-time-scale photovoltaic output time sequence |
| US20180375334A1 (en) * | 2017-06-26 | 2018-12-27 | Tsinghua University | Method and apparatus for photovoltaic power forecast based on numerical weather prediction |
| CN109165770A (en) * | 2018-07-09 | 2019-01-08 | 江苏大学 | Novel photovoltaic power forecasting method based on AFSA-Elman |
| CN109376897A (en) * | 2018-08-29 | 2019-02-22 | 广东工业大学 | A kind of short-term wind power forecast method based on hybrid algorithm |
| CN110503060A (en) * | 2019-08-28 | 2019-11-26 | 中南大学 | A kind of spectral signal denoising method and its system |
| CN111915084A (en) * | 2020-08-03 | 2020-11-10 | 国网山东省电力公司电力科学研究院 | Hybrid photovoltaic power generation power prediction method and system based on neural network |
| CN112949936A (en) * | 2021-03-29 | 2021-06-11 | 福州大学 | Short-term photovoltaic power prediction method based on similar-day wavelet transform and multilayer perceptron |
-
2021
- 2021-07-23 CN CN202110836483.9A patent/CN113779861B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103927593A (en) * | 2014-04-22 | 2014-07-16 | 国家电网公司 | Photovoltaic generation power prediction method based on self-learning composite data source autoregression model |
| US20180240200A1 (en) * | 2015-09-30 | 2018-08-23 | China Electric Power Research Institute Company Limited | Method and device for modeling a long-time-scale photovoltaic output time sequence |
| CN106446494A (en) * | 2016-05-11 | 2017-02-22 | 新疆大学 | Wavelet packet-neural network-based wind/photovoltaic power prediction method |
| CN106503851A (en) * | 2016-10-25 | 2017-03-15 | 国家电网公司 | A kind of improved Short-Term Load Forecasting Method based on wavelet analysises |
| CN106815659A (en) * | 2017-01-20 | 2017-06-09 | 国网浙江省电力公司电力科学研究院 | A kind of ultra-short term forecast of solar irradiance method and its device based on mixed model |
| CN107194496A (en) * | 2017-04-25 | 2017-09-22 | 甘肃省电力公司风电技术中心 | The Forecasting Methodology and prediction meanss of photovoltaic power |
| US20180375334A1 (en) * | 2017-06-26 | 2018-12-27 | Tsinghua University | Method and apparatus for photovoltaic power forecast based on numerical weather prediction |
| CN107563565A (en) * | 2017-09-14 | 2018-01-09 | 广西大学 | A kind of short-term photovoltaic for considering Meteorology Factor Change decomposes Forecasting Methodology |
| CN109165770A (en) * | 2018-07-09 | 2019-01-08 | 江苏大学 | Novel photovoltaic power forecasting method based on AFSA-Elman |
| CN109376897A (en) * | 2018-08-29 | 2019-02-22 | 广东工业大学 | A kind of short-term wind power forecast method based on hybrid algorithm |
| CN110503060A (en) * | 2019-08-28 | 2019-11-26 | 中南大学 | A kind of spectral signal denoising method and its system |
| CN111915084A (en) * | 2020-08-03 | 2020-11-10 | 国网山东省电力公司电力科学研究院 | Hybrid photovoltaic power generation power prediction method and system based on neural network |
| CN112949936A (en) * | 2021-03-29 | 2021-06-11 | 福州大学 | Short-term photovoltaic power prediction method based on similar-day wavelet transform and multilayer perceptron |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117076933A (en) * | 2023-10-16 | 2023-11-17 | 锦浪科技股份有限公司 | Training of arc judgment model, photovoltaic direct current arc detection method and computing equipment |
| CN117076933B (en) * | 2023-10-16 | 2024-02-06 | 锦浪科技股份有限公司 | Training of arc judgment model, photovoltaic direct current arc detection method and computing equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113779861B (en) | 2023-08-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Wu et al. | A novel hybrid system based on multi-objective optimization for wind speed forecasting | |
| Luo et al. | Design of a combined wind speed forecasting system based on decomposition-ensemble and multi-objective optimization approach | |
| Wang et al. | The study and application of a novel hybrid forecasting model–A case study of wind speed forecasting in China | |
| Duan et al. | A combined short-term wind speed forecasting model based on CNN–RNN and linear regression optimization considering error | |
| CN110309603B (en) | Short-term wind speed prediction method and system based on wind speed characteristics | |
| He et al. | A combined model for short-term wind power forecasting based on the analysis of numerical weather prediction data | |
| CN110264012B (en) | Renewable energy power combination prediction method and system based on empirical mode decomposition | |
| CN111832825B (en) | Wind power prediction method and system integrating long-term memory network and extreme learning machine | |
| Liang et al. | A combined model based on CEEMDAN, permutation entropy, gated recurrent unit network, and an improved bat algorithm for wind speed forecasting | |
| CN112288193A (en) | Ocean station surface salinity prediction method based on GRU deep learning of attention mechanism | |
| Zhang et al. | Photovoltaic power prediction based on hybrid modeling of neural network and stochastic differential equation | |
| Zhang et al. | Load prediction based on hybrid model of VMD-mRMR-BPNN-LSSVM | |
| CN115186923A (en) | Photovoltaic power generation power prediction method and device and electronic equipment | |
| CN112381673A (en) | Park electricity utilization information analysis method and device based on digital twin | |
| CN113779861B (en) | Photovoltaic Power Prediction Method and Terminal Equipment | |
| Sun et al. | Short-term power load prediction based on VMD-SG-LSTM | |
| Xu et al. | Interval prediction method for wind power based on VMD-ELM/ARIMA-ADKDE | |
| CN114154684A (en) | Short-term photovoltaic power prediction method based on data mining and multi-core support vector machine | |
| CN113837434A (en) | Solar photovoltaic power generation prediction method and device, electronic equipment and storage medium | |
| CN112906995A (en) | Photovoltaic power short-term prediction method based on EMD-FE-LSTM and iterative error correction | |
| CN115907131A (en) | Method and system for building electric heating load prediction model in northern area | |
| Wu et al. | Forecast of short-term electricity price based on data analysis | |
| CN115640903A (en) | Photovoltaic power generation prediction method and system considering wavelet decomposition and multi-objective optimization | |
| Zhang et al. | Short-term power load forecasting model design based on EMD-PSO-GRU | |
| CN114925940A (en) | Holiday load prediction method and system based on load decomposition |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |