CN113988394A - Wind power ultra-short-term power prediction method based on gram matrix and convolutional neural network - Google Patents
Wind power ultra-short-term power prediction method based on gram matrix and convolutional neural network Download PDFInfo
- Publication number
- CN113988394A CN113988394A CN202111226793.5A CN202111226793A CN113988394A CN 113988394 A CN113988394 A CN 113988394A CN 202111226793 A CN202111226793 A CN 202111226793A CN 113988394 A CN113988394 A CN 113988394A
- Authority
- CN
- China
- Prior art keywords
- historical
- wind
- power
- power prediction
- neural network
- 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
- 239000011159 matrix material Substances 0.000 title claims abstract description 57
- 238000013527 convolutional neural network Methods 0.000 title claims abstract description 40
- 238000000034 method Methods 0.000 title claims abstract description 28
- 230000004927 fusion Effects 0.000 claims abstract description 23
- 238000000354 decomposition reaction Methods 0.000 claims abstract description 14
- 238000010606 normalization Methods 0.000 claims abstract description 12
- 239000013598 vector Substances 0.000 claims description 20
- 238000004590 computer program Methods 0.000 claims description 14
- 238000010276 construction Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 3
- 238000010248 power generation Methods 0.000 abstract description 9
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000004364 calculation method Methods 0.000 description 3
- 238000013135 deep learning Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000000605 extraction Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000002156 mixing Methods 0.000 description 1
- 238000000053 physical method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 230000000306 recurrent effect Effects 0.000 description 1
- 238000007619 statistical method Methods 0.000 description 1
- 230000001052 transient effect Effects 0.000 description 1
Images
Classifications
-
- 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
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
- G06N3/045—Combinations of networks
-
- 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
- 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)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- Data Mining & Analysis (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- General Health & Medical Sciences (AREA)
- Software Systems (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- Pure & Applied Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Marketing (AREA)
- Mathematical Analysis (AREA)
- Artificial Intelligence (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Molecular Biology (AREA)
- Primary Health Care (AREA)
- Water Supply & Treatment (AREA)
- Public Health (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Wind Motors (AREA)
Abstract
The invention relates to a wind power ultra-short-term power prediction method based on a gram matrix and a convolutional neural network. The method is suitable for the field of wind power generation power prediction. The technical scheme adopted by the invention is as follows: a wind power ultra-short-term power prediction method based on a gram matrix and a convolutional neural network is characterized by comprising the following steps: acquiring historical wind speed, historical wind direction and historical power, wherein the historical wind speed, historical wind direction and historical power comprise wind speed, wind direction and power at n moments before a moment to be predicted; VMD decomposition is carried out on the historical power data to obtain m characteristic signals with different central frequencies; carrying out normalization processing on the historical wind speed, the historical wind direction and the characteristic signals; carrying out data fusion on the normalized historical wind speed, historical wind direction and characteristic signals, and constructing a gram matrix based on data obtained by data fusion; inputting the gram matrix into the trained wind power prediction model to obtain a power prediction result; the wind power prediction model is constructed based on a convolutional neural network.
Description
Technical Field
The invention relates to a wind power ultra-short-term power prediction method based on a gram matrix and a convolutional neural network. The method is suitable for the field of wind power generation power prediction.
Background
Wind energy is a novel energy source, and is widely used due to the characteristics of unlimited reserve, safety, cleanness and the like, so that the wind energy is vigorously developed in various countries. The randomness and the fluctuation of the wind power generation power are high due to the non-stationarity of the wind speed, the challenges are brought to the safe, stable and economic operation of large-scale wind power generation grid connection, and the accuracy rate of wind power generation power prediction needs to be improved.
Short-term and ultra-short-term prediction can provide reliable electric power transient information for electric power scheduling and wind power generation grid connection safety, and therefore wind power prediction research is mainly focused on short-term and ultra-short-term wind power prediction.
Wind power prediction is roughly divided into the following four types of (1) physical methods; (2) a statistical method; (3) a deep learning method; (4) and (3) a mixing method.
The deep learning method is very widely applied due to the simple modeling and high accuracy rate. The main body structures of the neural network commonly used in the deep learning method at present mainly comprise a Convolutional Neural Network (CNN) and a Recurrent Neural Network (RNN).
Convolutional neural networks are mainly used for processing data signals (such as images) with more than two dimensions, and circular neural networks are mainly used for processing data signals with one dimension, such as time sequence signals. Convolutional neural networks have enjoyed great success in the image field, mainly due to their powerful feature extraction capabilities of the network structure. The convolutional neural network can obtain the multilayer characteristics of the image, and can realize the fusion of deep-layer characteristics and shallow-layer characteristics in the modes of residual error structure, jump connection and the like, thereby greatly improving the prediction capability of the network.
Disclosure of Invention
The technical problem to be solved by the invention is as follows: the wind power ultra-short-term power prediction method based on the gram matrix and the convolutional neural network is provided.
The technical scheme adopted by the invention is as follows: a wind power ultra-short-term power prediction method based on a gram matrix and a convolutional neural network is characterized by comprising the following steps:
acquiring historical wind speed, historical wind direction and historical power, wherein the historical wind speed, historical wind direction and historical power comprise wind speed, wind direction and power at n moments before a moment to be predicted;
VMD decomposition is carried out on the historical power data to obtain m characteristic signals with different central frequencies;
carrying out normalization processing on the historical wind speed, the historical wind direction and the characteristic signals;
carrying out data fusion on the normalized historical wind speed, historical wind direction and characteristic signals, and constructing a gram matrix based on data obtained by data fusion;
inputting the gram matrix into the trained wind power prediction model to obtain a power prediction result; the wind power prediction model is constructed based on a convolutional neural network.
The data fusion of the normalized historical wind speed, historical wind direction and characteristic signals comprises the following steps:
obtaining 2 vectors of 1 x n after the historical wind speed and the historical wind direction are normalized, and obtaining m vectors of 1 x n after the characteristic signals are normalized;
and (m +2) vectors of 1 x n are obtained by fusing the historical wind speed, the historical wind direction and the characteristic signal data.
The constructing of the gram matrix based on the data obtained by data fusion comprises the following steps:
expanding (m +2) vectors of 1 × n obtained by data fusion to obtain (m +2) × n vectors of 1 × 1;
the (m +2) × n vectors 1 × 1 are subjected to a trellis matrix construction, and 1 ((m +2) × n) matrix is obtained.
The training of the wind power prediction model comprises the following steps:
and calculating the loss between the power prediction result and the real wind power by adopting an MSE loss function, reversely transmitting the acquired network loss, updating the weight of the wind power prediction model until the network converges, and acquiring the trained wind power prediction model.
The convolutional neural network employs vgg19 or resnet.
A wind power ultra-short term power prediction device based on a gram matrix and a convolutional neural network is characterized in that:
the historical data acquisition module is used for acquiring historical wind speed, historical wind direction and historical power, including wind speed, wind direction and power at n moments before the moment to be predicted;
the signal decomposition module is used for performing VMD decomposition on the historical power data to obtain m characteristic signals with different central frequencies;
the normalization processing module is used for performing normalization processing on the historical wind speed, the historical wind direction and the characteristic signals;
the gram matrix construction module is used for carrying out data fusion on the normalized historical wind speed, historical wind direction and characteristic signals and constructing a gram matrix based on data obtained by the data fusion;
the power prediction module is used for inputting the gram matrix into the trained wind power prediction model to obtain a power prediction result; the wind power prediction model is constructed based on a convolutional neural network.
A storage medium having stored thereon a computer program executable by a processor, the computer program comprising: the computer program when executed implements the steps of the wind power ultra-short term power prediction method based on the gram matrix and the convolutional neural network.
An ultra-short term wind power prediction device having a memory and a processor, the memory having stored thereon a computer program executable by the processor, the device comprising: the computer program when executed implements the steps of the wind power ultra-short term power prediction method based on the gram matrix and the convolutional neural network.
The invention has the beneficial effects that: according to the method, the historical power data are subjected to VMD decomposition to obtain a plurality of characteristic signals with different central frequencies, a gram matrix is constructed by combining the historical wind speed and the historical wind direction, one-dimensional wind power signals are converted into two-dimensional signals based on the gram matrix, a convolutional neural network is combined with two-position signals to predict ultra-short-term wind power, and the wind power prediction precision is improved.
Drawings
FIG. 1 is a flow chart of an embodiment.
Detailed Description
In the wind power prediction task, historical data including multiple time points, including one-dimensional time sequence signals such as wind speed, wind direction, power and temperature, are acquired, and when a two-dimensional convolution neural network is used for wind power prediction, dimension-increasing processing needs to be performed on the data.
The embodiment is a wind power ultra-short-term power prediction method based on a gram matrix and a convolutional neural network, and specifically comprises the following steps:
and S1, acquiring historical wind speed, historical wind direction and historical power, wherein the historical wind speed, historical wind direction and historical power comprise the wind speed, the wind direction and the power at n times before the time to be predicted.
Wind power generation is the conversion of wind energy into electrical energy, with wind speed and direction closely related to the wind power generation power. The historical power of wind power generation has time sequence correlation with the wind power at the future moment, so the wind speed, the wind direction and the historical power are selected as the input characteristics of the wind power prediction model in the embodiment.
Selecting the length of the time sequence: in the embodiment, correlation degrees between all variables in original wind power data and wind power are measured by using a Pearson coefficient, historical wind speed, wind direction and wind power at n moments with Pearson coefficients larger than 0.8 (strong correlation) are selected, and n is 8 through calculation.
And S2, performing VMD decomposition on the historical power data to obtain m (m is 8) characteristic signals with different center frequencies.
The Variational Modal Decomposition (VMD) is a new self-adaptive signal processing method, and has good processing effect on non-stationary and non-linear signals. VMD decomposition is carried out on the historical power data, multidimensional characteristics of the data can be obtained, and extracted historical wind power information is enriched. The historical power signal is decomposed by VMD to obtain 8 characteristic signals with different center frequencies.
And S3, carrying out normalization processing on the historical wind speed, the historical wind direction and the characteristic signals. In order to eliminate dimension influence among data and facilitate quick convergence in a subsequent network training stage, the method carries out min-max standardization on historical wind speed and historical wind direction and decomposed wind power data, and is shown as a formula (1):
after normalization, the characteristic signals of the historical wind speed data, the historical wind direction data and the historical wind power data are all located in the range of [0, 1], and feature learning of a subsequent network is facilitated.
And S4, carrying out data fusion on the normalized historical wind speed, historical wind direction and characteristic signals, and constructing a gram matrix based on data obtained by the data fusion.
The historical wind speed data and the historical wind direction data are normalized to obtain 2 vectors of 1 x 8, the historical power data are decomposed and normalized through VMD to obtain 8 vectors of 1 x 8, and the 10 vectors of 1 x 8 are obtained through data fusion.
After 10 vectors of 1 × 8 obtained by data fusion are expanded, 80 vectors of 1 × 1 are obtained, and a trellis matrix is constructed for 80 vectors of 1 × 1, thereby obtaining 1 matrix of 80 × 80.
Any k vectors in the n-dimensional Euclidean space are pairwise calculated to form a matrix formed by inner products, and the matrix is called a Gram matrix (Gram matrix) of the k vectors. The wind power data which is originally one-dimensional can be converted into two-dimensional data through the gram matrix, and feature extraction and future information prediction can be conveniently carried out subsequently by using a Convolutional Neural Network (CNN).
And S5, inputting the gram matrix into a trained wind power prediction model constructed based on the convolutional neural network to obtain a power prediction result.
And step S4, obtaining a two-dimensional gram matrix as the input of the wind power prediction model. The data of the input model is similar to the two-dimensional image of the computer vision field, so the adopted structural network can be a classical convolution neural network of the image field, such as vgg19-net and resnet.
In the embodiment, the wind power prediction loss is calculated by adopting an MSE loss function during the training of the electric power prediction model, and the calculation is as shown in a formula (2):
wherein, PtrueRepresenting true wind power, PpredRepresenting the wind power predicted by the network.
Performing back propagation on the network loss obtained by calculation, and updating parameters of the wind power prediction model until the prediction model is converged; and obtaining a final wind power prediction model for subsequent wind power prediction.
According to the wind power prediction method, the historical wind speed, the historical wind direction and the historical power are combined, the structural gram matrix is adopted for carrying out dimensionality-increasing operation, the convolutional neural network is used for predicting, and the wind power prediction effect when the wind speed changes suddenly is effectively improved.
The embodiment also provides a wind power ultra-short-term power prediction device based on the gram matrix and the convolutional neural network, which comprises a historical data acquisition module, a signal decomposition module, a normalization processing module, a gram matrix construction module and a power prediction module.
In the embodiment, the historical data acquisition module is used for acquiring historical wind speed, historical wind direction and historical power, including wind speed, wind direction and power at 8 moments before the moment to be predicted; the signal decomposition module is used for performing VMD decomposition on the historical power data to obtain 8 characteristic signals with different central frequencies; the normalization processing module is used for performing normalization processing on the historical wind speed, the historical wind direction and the characteristic signals; the gram matrix construction module is used for carrying out data fusion on the normalized historical wind speed, historical wind direction and characteristic signals and constructing a gram matrix based on data obtained by the data fusion; and the power prediction module is used for inputting the gram matrix into a trained wind power prediction model constructed based on the convolutional neural network to obtain a power prediction result.
The present embodiment also provides a storage medium on which a computer program executable by a processor is stored, where the computer program is executed to implement the steps of the wind power ultra-short term power prediction method based on the gram matrix and the convolutional neural network in the present embodiment.
The embodiment also provides wind power ultra-short term power prediction equipment which is provided with a memory and a processor, wherein the memory is stored with a computer program capable of being executed by the processor, and when the computer program is executed, the steps of the wind power ultra-short term power prediction method based on the gram matrix and the convolutional neural network in the embodiment are realized.
Claims (8)
1. A wind power ultra-short-term power prediction method based on a gram matrix and a convolutional neural network is characterized by comprising the following steps:
acquiring historical wind speed, historical wind direction and historical power, wherein the historical wind speed, historical wind direction and historical power comprise wind speed, wind direction and power at n moments before a moment to be predicted;
VMD decomposition is carried out on the historical power data to obtain m characteristic signals with different central frequencies;
carrying out normalization processing on the historical wind speed, the historical wind direction and the characteristic signals;
carrying out data fusion on the normalized historical wind speed, historical wind direction and characteristic signals, and constructing a gram matrix based on data obtained by data fusion;
inputting the gram matrix into the trained wind power prediction model to obtain a power prediction result; the wind power prediction model is constructed based on a convolutional neural network.
2. The wind power ultra-short term power prediction method based on the gram matrix and the convolutional neural network as claimed in claim 1, wherein the data fusion of the normalized historical wind speed, historical wind direction and characteristic signal comprises:
obtaining 2 vectors of 1 x n after the historical wind speed and the historical wind direction are normalized, and obtaining m vectors of 1 x n after the characteristic signals are normalized;
and (m +2) vectors of 1 x n are obtained by fusing the historical wind speed, the historical wind direction and the characteristic signal data.
3. The wind power ultra-short term power prediction method based on the gram matrix and the convolutional neural network as claimed in claim 2, wherein the constructing the gram matrix based on the data obtained by data fusion comprises:
expanding (m +2) vectors of 1 × n obtained by data fusion to obtain (m +2) × n vectors of 1 × 1;
the (m +2) × n vectors 1 × 1 are subjected to a trellis matrix construction, and 1 ((m +2) × n) matrix is obtained.
4. The wind power ultra-short term power prediction method based on the gram matrix and the convolutional neural network as claimed in claim 1, wherein the training of the wind power prediction model comprises:
and calculating the loss between the power prediction result and the real wind power by adopting an MSE loss function, reversely transmitting the acquired network loss, updating the weight of the wind power prediction model until the network converges, and acquiring the trained wind power prediction model.
5. The ultra-short-term wind power prediction method based on the gram matrix and the convolutional neural network as claimed in claim 1 or 4, wherein: the convolutional neural network employs vgg19 or resnet.
6. A wind power ultra-short term power prediction device based on a gram matrix and a convolutional neural network is characterized in that:
the historical data acquisition module is used for acquiring historical wind speed, historical wind direction and historical power, including wind speed, wind direction and power at n moments before the moment to be predicted;
the signal decomposition module is used for performing VMD decomposition on the historical power data to obtain m characteristic signals with different central frequencies;
the normalization processing module is used for performing normalization processing on the historical wind speed, the historical wind direction and the characteristic signals;
the gram matrix construction module is used for carrying out data fusion on the normalized historical wind speed, historical wind direction and characteristic signals and constructing a gram matrix based on data obtained by the data fusion;
the power prediction module is used for inputting the gram matrix into the trained wind power prediction model to obtain a power prediction result; the wind power prediction model is constructed based on a convolutional neural network.
7. A storage medium having stored thereon a computer program executable by a processor, the computer program comprising: the computer program is executed to realize the steps of the wind power ultra-short-term power prediction method based on the gram matrix and the convolutional neural network in any one of claims 1 to 5.
8. An ultra-short term wind power prediction device having a memory and a processor, the memory having stored thereon a computer program executable by the processor, the device comprising: the computer program is executed to realize the steps of the wind power ultra-short-term power prediction method based on the gram matrix and the convolutional neural network in any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111226793.5A CN113988394A (en) | 2021-10-21 | 2021-10-21 | Wind power ultra-short-term power prediction method based on gram matrix and convolutional neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111226793.5A CN113988394A (en) | 2021-10-21 | 2021-10-21 | Wind power ultra-short-term power prediction method based on gram matrix and convolutional neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113988394A true CN113988394A (en) | 2022-01-28 |
Family
ID=79739939
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111226793.5A Pending CN113988394A (en) | 2021-10-21 | 2021-10-21 | Wind power ultra-short-term power prediction method based on gram matrix and convolutional neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113988394A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117933363A (en) * | 2024-03-08 | 2024-04-26 | 广东工业大学 | Method and system for predicting short-term wind power of newly-built wind power plant based on sample migration |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108470209A (en) * | 2018-03-27 | 2018-08-31 | 北京工业大学 | A kind of convolutional Neural net method for visualizing based on gram matrix regularization |
| CN108549929A (en) * | 2018-03-29 | 2018-09-18 | 河海大学 | A kind of photovoltaic power prediction technique based on deep layer convolutional neural networks |
| CN109146192A (en) * | 2018-09-03 | 2019-01-04 | 贵州电网有限责任公司 | A kind of wind power forecasting method considering running of wind generating set operating condition |
| CN110363360A (en) * | 2019-07-24 | 2019-10-22 | 广东工业大学 | A kind of short-term wind power forecast method, device and equipment |
| CN111160621A (en) * | 2019-12-06 | 2020-05-15 | 江苏方天电力技术有限公司 | Short-term wind power prediction method integrating multi-source information |
| CN111461444A (en) * | 2020-04-07 | 2020-07-28 | 上海电气风电集团股份有限公司 | Prediction method, system, medium and electronic device for unit power of wind power plant |
| CN112418553A (en) * | 2020-12-07 | 2021-02-26 | 江苏科技大学 | Offshore wind power control method based on VMD-CNN network |
| CN112434848A (en) * | 2020-11-19 | 2021-03-02 | 西安理工大学 | Nonlinear weighted combination wind power prediction method based on deep belief network |
| CN112836434A (en) * | 2021-02-22 | 2021-05-25 | 中国电建集团华东勘测设计研究院有限公司 | Wind power ultra-short-term power prediction method integrating time sequence characteristics and statistical characteristics |
| CN112990553A (en) * | 2021-02-23 | 2021-06-18 | 中国电建集团华东勘测设计研究院有限公司 | Wind power ultra-short-term power prediction method using self-attention mechanism and bilinear fusion |
| CN113837499A (en) * | 2021-11-24 | 2021-12-24 | 中国电建集团江西省电力设计院有限公司 | Ultra-short-term wind power prediction method and system |
-
2021
- 2021-10-21 CN CN202111226793.5A patent/CN113988394A/en active Pending
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108470209A (en) * | 2018-03-27 | 2018-08-31 | 北京工业大学 | A kind of convolutional Neural net method for visualizing based on gram matrix regularization |
| CN108549929A (en) * | 2018-03-29 | 2018-09-18 | 河海大学 | A kind of photovoltaic power prediction technique based on deep layer convolutional neural networks |
| CN109146192A (en) * | 2018-09-03 | 2019-01-04 | 贵州电网有限责任公司 | A kind of wind power forecasting method considering running of wind generating set operating condition |
| CN110363360A (en) * | 2019-07-24 | 2019-10-22 | 广东工业大学 | A kind of short-term wind power forecast method, device and equipment |
| CN111160621A (en) * | 2019-12-06 | 2020-05-15 | 江苏方天电力技术有限公司 | Short-term wind power prediction method integrating multi-source information |
| CN111461444A (en) * | 2020-04-07 | 2020-07-28 | 上海电气风电集团股份有限公司 | Prediction method, system, medium and electronic device for unit power of wind power plant |
| CN112434848A (en) * | 2020-11-19 | 2021-03-02 | 西安理工大学 | Nonlinear weighted combination wind power prediction method based on deep belief network |
| CN112418553A (en) * | 2020-12-07 | 2021-02-26 | 江苏科技大学 | Offshore wind power control method based on VMD-CNN network |
| CN112836434A (en) * | 2021-02-22 | 2021-05-25 | 中国电建集团华东勘测设计研究院有限公司 | Wind power ultra-short-term power prediction method integrating time sequence characteristics and statistical characteristics |
| CN112990553A (en) * | 2021-02-23 | 2021-06-18 | 中国电建集团华东勘测设计研究院有限公司 | Wind power ultra-short-term power prediction method using self-attention mechanism and bilinear fusion |
| CN113837499A (en) * | 2021-11-24 | 2021-12-24 | 中国电建集团江西省电力设计院有限公司 | Ultra-short-term wind power prediction method and system |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117933363A (en) * | 2024-03-08 | 2024-04-26 | 广东工业大学 | Method and system for predicting short-term wind power of newly-built wind power plant based on sample migration |
| CN117933363B (en) * | 2024-03-08 | 2024-06-11 | 广东工业大学 | Method and system for predicting short-term wind power of newly-built wind power plant based on sample migration |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110175386B (en) | Method for predicting temperature of electrical equipment of transformer substation | |
| CN113011570B (en) | Facial expression recognition method adopting neural network compression system | |
| CN113988449B (en) | Wind power prediction method based on transducer model | |
| CN111930894A (en) | Long text matching method and device, storage medium and electronic equipment | |
| CN109471049B (en) | Satellite power supply system anomaly detection method based on improved stacked self-encoder | |
| Yan et al. | Learning probabilistic multi-modal actor models for vision-based robotic grasping | |
| CN113988394A (en) | Wind power ultra-short-term power prediction method based on gram matrix and convolutional neural network | |
| CN111401261B (en) | Robot gesture recognition method based on GAN-CNN framework | |
| CN111080001A (en) | Deep neural network prediction method applied to wind speed of wind power plant | |
| CN112241802A (en) | Interval prediction method for wind power | |
| CN116862080B (en) | Carbon emission prediction method and system based on double-view contrast learning | |
| CN117669699A (en) | Digital twinning-oriented semantic information federation learning method and system in industrial Internet of things scene | |
| Suroso et al. | Synthesis of a small fingerprint database through a deep generative model for indoor localisation | |
| CN115577647B (en) | Power grid fault type identification method and intelligent agent construction method | |
| CN116542315A (en) | Large-scale neural network parameter compression method and system based on tensor decomposition | |
| CN113780661B (en) | Wind power ultra-short-term power prediction method for abrupt wind speed | |
| CN113964825A (en) | Ultrashort-term wind power prediction method based on secondary decomposition and BiGRU | |
| CN113988395A (en) | Wind power ultra-short-term power prediction method based on SSD and dual attention mechanism BiGRU | |
| CN114550159A (en) | Image subtitle generating method, device and equipment and readable storage medium | |
| CN114065834A (en) | Model training method, terminal device and computer storage medium | |
| Li et al. | Scenario Generation of Renewable Energy Based on Improved Diffusion Model | |
| Li et al. | Fast scenario reduction for power systems by deep learning | |
| Liu et al. | Sentiment analysis of MOOC reviews based on capsule network | |
| CN117436443B (en) | Model construction method, text generation method, device, equipment and medium | |
| CN117875508A (en) | Knowledge distillation-based solar irradiance multi-modal short-term prediction method |
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 |