CN112633632A - Integrated short-term wind power cluster power prediction method based on signal decomposition technology - Google Patents
Integrated short-term wind power cluster power prediction method based on signal decomposition technology Download PDFInfo
- Publication number
- CN112633632A CN112633632A CN202011352009.0A CN202011352009A CN112633632A CN 112633632 A CN112633632 A CN 112633632A CN 202011352009 A CN202011352009 A CN 202011352009A CN 112633632 A CN112633632 A CN 112633632A
- Authority
- CN
- China
- Prior art keywords
- prediction
- vmd
- data
- integrated
- sdae
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 33
- 238000000354 decomposition reaction Methods 0.000 title claims abstract description 26
- 238000005516 engineering process Methods 0.000 title claims abstract description 22
- 238000012360 testing method Methods 0.000 claims abstract description 14
- 238000012549 training Methods 0.000 claims abstract description 14
- 238000011156 evaluation Methods 0.000 claims abstract description 6
- 238000007781 pre-processing Methods 0.000 claims abstract description 6
- 238000013527 convolutional neural network Methods 0.000 claims description 21
- 238000012706 support-vector machine Methods 0.000 claims description 11
- 238000013528 artificial neural network Methods 0.000 claims description 4
- 238000002156 mixing Methods 0.000 claims description 3
- 238000000489 vacuum metal deposition Methods 0.000 claims description 3
- 238000013473 artificial intelligence Methods 0.000 description 4
- 230000010354 integration Effects 0.000 description 2
- 238000010248 power generation Methods 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 238000013179 statistical model Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000005855 radiation 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0637—Strategic management or analysis, e.g. setting a goal or target of an organisation; Planning actions based on goals; Analysis or evaluation of effectiveness of goals
- G06Q10/06375—Prediction of business process outcome or impact based on a proposed change
-
- 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
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Entrepreneurship & Innovation (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- Public Health (AREA)
- Water Supply & Treatment (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Wind Motors (AREA)
Abstract
The invention discloses an integrated short-term wind power cluster power prediction method based on a signal decomposition technology, which is characterized in that collected NWP data and corresponding power data are divided into two independent data sets for prediction model training and testing; carrying out data preprocessing on the training data by a VMD (virtual machine format) and WT (WT) method, and predicting the preprocessed data by using models with SDAE (software development instrumentation), LSTM (Link State TM), BilsTM (TM) and CNN (CNN) as cores respectively to obtain sub-prediction results; the sub-prediction results respectively construct sub-prediction models through PLSR, BPNN and SVM network types, and weights are distributed to each sub-prediction result according to different accuracy degrees of the sub-prediction models to form a WPP prediction model; and selecting the most appropriate integrated prediction model for the WPP integrated prediction model performance evaluation standard, inputting the test data set of S1 into the selected integrated prediction model, performing prediction, and outputting a result. The method has the advantages of high prediction precision, wide data application range and popularization value.
Description
Technical Field
The invention relates to an integrated short-term wind power cluster power prediction method based on a signal decomposition technology, and belongs to the field of new energy power prediction.
Background
With the gradual depletion of primary energy sources such as fossil energy, the use of clean energy sources such as wind energy and the like occupies an increasingly important position in the energy field. However, compared with the utilization of the traditional energy, the wind energy is greatly influenced by the environment, is easily influenced by meteorological conditions, solar radiation and the like, and has low energy density and unstable power. If the wind power generation system is successfully merged into a power grid, the wind power needs to be accurately predicted, so that a scientific power generation plan is made, and the reduction of the operation cost of the power grid is facilitated.
At present, the power of a wind power cluster is predicted mainly by two ways, one is to predict the power by a statistical model, and the other is to predict the power by an artificial intelligence method. For the statistical model, the expert dependence is high, and the intelligence degree is low; most of the existing methods for predicting the wind power through artificial intelligence are predicted through a single neural network, the data information is not comprehensively mastered, the prediction result is influenced by the environment and the like to a greater extent, and the high robustness is poor. The method for predicting the wind power by integrating the artificial intelligence of the Short-Term wind power cluster power prediction method based on the signal decomposition technology can capture more data characteristics, integrates the advantages of data integration of the Short-Term wind power cluster prediction methods of SDAE (staged Denoising Autoencoder), LSTM (Long Short-Term Memory), Bi-directional Long Short-Term Memory and CNN (volumetric Neural networks), obtains more data characteristic information by using an artificial intelligence means, and improves the accuracy and robustness of prediction.
Disclosure of Invention
The invention aims to provide an integrated short-term wind power cluster power prediction method based on a signal decomposition technology, so as to solve the problems in the background technology.
The purpose of the invention is realized by the following technical measures:
an integrated short-term wind power cluster power prediction method based on a signal decomposition technology comprises the following steps:
s1: collecting wind power plant data for training and testing a prediction model;
s2: respectively preprocessing data input into a prediction model by two signal decomposition technologies of VMD (spatial Mode decomposition) and WT (wavelet transform);
s3: predicting the data preprocessed by S2 through a model taking SDAE, LSTM, BilSTM and CNN as cores respectively to obtain sub-prediction results of VMD-SDAE, VMD-LSTM, VMD-BilSTM, VMD-CNN, WT-SDAE, WT-LSTM, WT-BilSTM and WT-CNN;
s4: sub-prediction models are respectively constructed through three network models, namely PLSR (partial Least Square regression), BPNN (Back prediction Neural network) and SVM (support vector machines), and weights are distributed to each sub-prediction result of S3 according to different accuracy degrees of the sub-prediction models to form a WPP (wind Power prediction) prediction model;
s5: taking NRMSE (normalized root mean square error) and NMAE (normalized mean absolute error) as WPP integrated prediction model performance evaluation standards, selecting the most appropriate integrated prediction model, inputting the test data of S1 into the selected integrated prediction model, then performing prediction, and outputting the result.
Further, the wind farm data collected in the step S1 includes the collected NWP data set with the wind farm time resolution of 1 hour and the corresponding power data thereof, 70% of the data is used for training the prediction model, and 30% of the data is used for testing the integrated prediction model;
further, the specific step of S2 includes: using VMDs with the number of modes of 5-14 to preprocess data used for predictive model training to obtain 10 groups of preprocessed data, using 12 mother wavelets and 24 different wavelet parameters to preprocess the data used for predictive model training by a WT decomposition method to obtain 24 groups of preprocessed data, and obtaining 34 groups of preprocessed data in total;
further, the specific step of S3 includes: respectively inputting the 34 groups of data preprocessed by the VMD and WT signal decomposition technologies in the step S2 into a network model taking SDAE, LSTM, BilSTM and CNN as cores for prediction to obtain VMD-SDAE, VMD-LSTM, VMD-BilSTM, VMD-CNN and WT-SDAE, WT-LSTM, WT-BilSTM and WT-CNN sub-prediction results which meet the requirements under the SDAE containing damaged data characteristics, LSTM and BilSTM time sequence characteristics and CNN map characteristics;
further, the specific step of S4 includes:
s4.1: at the blending layer, PLSR, BPNN and SVM network models are respectively used to respectively form VMD-WT-SDAE-PLSR, VMD-WT-LSTM-PLSR, VMD-WT-BilSTM-PLSR, VMD-WT-CNN-PLSR, VMD-WT-SDAE-BPNN, VMD-WT-LSTM-BPNN, VMD-WT-BilSTM-BPNN, VMD-WT-CNN-BPNN and VMD-WT-SDAE-SVM, VMD-WT-LSTM-SVM, VMD-WT-BilSTM-SVM and VMD-WT-CNN-SVM sub-prediction models;
s4.2: and distributing weights to the sub-prediction results in the S3 through a PLSR, a BPNN and an SVM network model according to different accuracies of the sub-prediction models to obtain a WPP integrated prediction model of the VMD-WT-SDAE-PLSR, the VMD-WT-SDAE-BPNN and the VMD-WT-SDAE-SVM.
Further, the step of S5 includes: the method comprises the steps of taking NRMSE and NMAE as WPP integrated prediction model performance evaluation standards, selecting a WPP integrated prediction model with the optimal parameters as a short-term wind power cluster power prediction model, using 30% of test data of S1 to select the most appropriate WPP integrated prediction model to perform prediction, and outputting results.
The invention achieves the following beneficial effects: the method increases the diversity of errors and the integration of submodels through the modern signal decomposition technology VMD and WT so as to improve the prediction performance, improves the prediction precision under the condition of containing noise through an SDAE core prediction model, considers the prediction precision into the final result through constructing three integrated prediction modes, improves the final prediction precision, and plays an important role in wind power prediction.
Drawings
Fig. 1 is a block diagram of the overall flow structure of the present invention.
Detailed Description
The invention provides a short-term wind power cluster power prediction method based on integrated SDAE, LSTM, BiLSTM and CNN, which is used for predicting data based on a large number of samples and improving wind power prediction accuracy.
As shown in fig. 1, an integrated short-term wind power cluster power prediction method based on a signal decomposition technology includes the following steps:
s1: the method comprises the following steps of collecting wind power plant data for training and testing a prediction model, wherein the specific steps comprise:
acquiring wind power plant data, including an acquired NWP (non-Newton P) data set with the time resolution of 1 hour of the wind power plant and corresponding power data, wherein 70% of the data is used for training a prediction model, and 30% of the data is used for testing an integrated prediction model;
s2: data preprocessing is respectively carried out on data input into a prediction model through two signal decomposition technologies of VMD and WT, and the method specifically comprises the following steps:
using VMDs with the mode numbers of 5-14 to carry out data preprocessing on data used for predictive model training to obtain 10 groups of preprocessed data, preprocessing the data used for predictive model training by using 12 mother wavelets and 24 different wavelet parameters through a WT decomposition method to obtain 24 groups of preprocessed data, and obtaining 34 groups of preprocessed data in total;
s3: predicting the data preprocessed by S2 through a model with SDAE, LSTM, BilSTM and CNN as cores respectively to obtain sub-prediction results, wherein the method comprises the following specific steps: inputting the 34 groups of data preprocessed by the VMD and WT signal decomposition technologies in the step S2 into a network model taking SDAE, LSTM, BilSTM and CNN as cores for prediction to obtain VMD-SDAE, VMD-LSTM, VMD-Bil STM, VMD-CNN and WT-SDAE, WT-LSTM, WT-BilSTM and WT-CNN sub-prediction results which meet the requirements and are under the SDAE containing damaged data characteristics, LSTM and BilTM time sequence characteristics and CNN map characteristics;
s4: the method comprises the following steps of respectively constructing sub-prediction models through three network models of PLSR, BPNN and SVM, distributing weight to each sub-prediction result of S3 according to different accuracy degrees of the sub-prediction models to form the WPP integrated prediction model, wherein the method specifically comprises the following steps:
s4.1: at the blending layer, PLSR, BPNN and SVM network models are respectively used to respectively form VMD-WT-SDAE-PLSR, VMD-WT-LSTM-PLSR, VMD-WT-BilSTM-PLSR, VMD-WT-CNN-PLSR, VMD-WT-SDAE-BPNN, VMD-WT-LSTM-BPNN, VMD-WT-BilSTM-BPNN, VMD-WT-CNN-BPNN and VMD-WT-SDAE-SVM, VMD-WT-LSTM-SVM, VMD-WT-BilSTM-SVM and VMD-WT-CNN-SVM sub-prediction models;
s4.2: and distributing weights to the sub-prediction results in the S3 through a PLSR, a BPNN and an SVM network model according to different accuracies of the sub-prediction models to obtain a VMD-WT-SDAE-PLSR, a VMD-WT-SDAE-BPNN and a WPP sub-prediction model of the VMD-WT-SDAE-SVM.
S5: and (4) selecting the most appropriate integrated prediction model by taking NRMSE and NMAE as WPP integrated prediction model performance evaluation standards, inputting the test data of S1 into the selected integrated prediction model, then performing prediction, and outputting a result. The method comprises the following specific steps: the method comprises the steps of taking NRMSE and NMAE as WPP integrated prediction model performance evaluation standards, selecting a WPP integrated prediction model with the optimal parameters as a short-term wind power cluster power prediction model, using 30% of test data of S1 to select the most appropriate WPP integrated prediction model to perform prediction, and outputting results.
Claims (6)
1. An integrated short-term wind power cluster power prediction method based on a signal decomposition technology is characterized by comprising the following steps:
s1: collecting wind power plant data for training and testing a prediction model;
s2: respectively preprocessing data input into a prediction model by two signal decomposition technologies of VMD (spatial Mode decomposition) and WT (wavelet transform);
s3: predicting the data preprocessed by S2 through a model taking SDAE, LSTM, BilSTM and CNN as cores respectively to obtain sub-prediction results of VMD-SDAE, VMD-LSTM, VMD-BilSTM, VMD-CNN, WT-SDAE, WT-LSTM, WT-BilSTM and WT-CNN;
s4: sub-prediction models are respectively constructed through three network models, namely PLSR (partial Least Square regression), BPNN (Back prediction Neural network) and SVM (support vector machines), and weights are distributed to each sub-prediction result of S3 according to different accuracy degrees of the sub-prediction models to form a WPP (wind Power prediction) prediction model;
s5: taking NRMSE (normalized root mean square error) and NMAE (normalized mean absolute error) as WPP integrated prediction model performance evaluation standards, selecting the most appropriate integrated prediction model, inputting the test data of S1 into the selected integrated prediction model, then performing prediction, and outputting the result.
2. The integrated short-term wind power cluster power prediction method based on the signal decomposition technology as claimed in claim 1, characterized in that: in the step S1, the wind farm data collected in the step S1 includes the collected NWP data set with the wind farm time resolution of 1 hour and the corresponding power data thereof, 70% of the data is used for training the prediction model, and 30% of the data is used for testing the integrated prediction model.
3. The integrated short-term wind power cluster power prediction method based on the signal decomposition technology as claimed in claim 1, characterized in that: the specific step S2 in the step S2 includes: the data used for predictive model training is preprocessed by using VMDs with the number of modes of 5-14 respectively to obtain 10 groups of preprocessed data, and the data used for predictive model training is preprocessed by using 12 mother wavelets and 24 different wavelet parameters by a WT decomposition method to obtain 24 groups of preprocessed data, so that 34 groups of preprocessed data are obtained.
4. The integrated short-term wind power cluster power prediction method based on the signal decomposition technology as claimed in claim 1, characterized in that: and in the step S3, the data preprocessed by the 34 groups of signal decomposition technologies of VMD and WT in the step S2 are respectively input into a network model taking SDAE, LSTM, BilsTM and CNN as cores for prediction, and sub-prediction results meeting the requirements of VMD-SDAE, VMD-LSTM, VMD-BilsTM, VMD-CNN and WT-SDAE, WT-LSTM, WT-BilsTM and WT-CNN under the condition that the SDAE contains damaged data characteristics, LSTM and BilsTM time sequence characteristics and CNN map characteristics are obtained.
5. The integrated short-term wind power cluster power prediction method based on the signal decomposition technology is characterized by comprising the following steps of: in the step S4, an integrated WPP prediction model is formed, and the specific steps include:
s4.1: at the blending layer, PLSR, BPNN and SVM network models are respectively used to respectively form VMD-WT-SDAE-PLSR, VMD-WT-LSTM-PLSR, VMD-WT-BilSTM-PLSR, VMD-WT-CNN-PLSR, VMD-WT-SDAE-BPNN, VMD-WT-LSTM-BPNN, VMD-WT-BilSTM-BPNN, VMD-WT-CNN-BPNN and VMD-WT-SDAE-SVM, VMD-WT-LSTM-SVM, VMD-WT-BilSTM-SVM and VMD-WT-CNN-SVM sub-prediction models;
s4.2: and distributing weights to the sub-prediction results in the S3 through a PLSR, a BPNN and an SVM network model according to different accuracies of the sub-prediction models to obtain a WPP integrated prediction model of the VMD-WT-SDAE-PLSR, the VMD-WT-SDAE-BPNN and the VMD-WT-SDAE-SVM.
6. The integrated short-term wind power cluster power prediction method based on the signal decomposition technology as claimed in claim 1, characterized in that: in the step S5, NRMSE and NMAE are used as WPP integrated prediction model performance judgment standards, a WPP integrated prediction model with the optimal parameters is selected as a short-term wind power cluster power prediction model, 30% of test data of S1 is used for selecting the most appropriate WPP integrated prediction model to perform prediction, and a result is output.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011352009.0A CN112633632A (en) | 2020-11-26 | 2020-11-26 | Integrated short-term wind power cluster power prediction method based on signal decomposition technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011352009.0A CN112633632A (en) | 2020-11-26 | 2020-11-26 | Integrated short-term wind power cluster power prediction method based on signal decomposition technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112633632A true CN112633632A (en) | 2021-04-09 |
Family
ID=75304159
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011352009.0A Withdrawn CN112633632A (en) | 2020-11-26 | 2020-11-26 | Integrated short-term wind power cluster power prediction method based on signal decomposition technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112633632A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113221458A (en) * | 2021-05-17 | 2021-08-06 | 上海交通大学 | Multi-step prediction method and system for shield cutter head torque |
| CN113792919A (en) * | 2021-09-02 | 2021-12-14 | 华中科技大学 | Wind power prediction method based on combination of transfer learning and deep learning |
| CN114330935A (en) * | 2022-03-10 | 2022-04-12 | 南方电网数字电网研究院有限公司 | New energy power prediction method and system based on multiple combined strategy integrated learning |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106875033A (en) * | 2016-12-26 | 2017-06-20 | 华中科技大学 | A kind of wind-powered electricity generation cluster power forecasting method based on dynamic self-adapting |
| CN110443725A (en) * | 2019-08-14 | 2019-11-12 | 国网甘肃省电力公司信息通信公司 | Wind power prediction model based on CNN+LSTM |
| CN110751317A (en) * | 2019-09-26 | 2020-02-04 | 上海电力大学 | Power load prediction system and prediction method |
-
2020
- 2020-11-26 CN CN202011352009.0A patent/CN112633632A/en not_active Withdrawn
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106875033A (en) * | 2016-12-26 | 2017-06-20 | 华中科技大学 | A kind of wind-powered electricity generation cluster power forecasting method based on dynamic self-adapting |
| CN110443725A (en) * | 2019-08-14 | 2019-11-12 | 国网甘肃省电力公司信息通信公司 | Wind power prediction model based on CNN+LSTM |
| CN110751317A (en) * | 2019-09-26 | 2020-02-04 | 上海电力大学 | Power load prediction system and prediction method |
Non-Patent Citations (2)
| Title |
|---|
| DESI PURWATI: ""基于长短期记忆的短期负荷预测研究"", 《中国优秀博硕士学位论文全文数据库（硕士） 工程科技II辑》, 15 January 2020 (2020-01-15), pages 24 - 29 * |
| 彭小圣 等: ""A_Three-Stage_Ensemble_Short-Term_Wind_Power_Prediction_Method_Based_on_VMD-WT_Transform_and_SDAE_Deep_Learning"", 《HTTPS://IEEEXPLORE.IEEE.ORG/STAMP/STAMP.JSP?TP=&ARNUMBER=9208460》, 29 September 2020 (2020-09-29), pages 1350 - 1356 * |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113221458A (en) * | 2021-05-17 | 2021-08-06 | 上海交通大学 | Multi-step prediction method and system for shield cutter head torque |
| CN113792919A (en) * | 2021-09-02 | 2021-12-14 | 华中科技大学 | Wind power prediction method based on combination of transfer learning and deep learning |
| CN113792919B (en) * | 2021-09-02 | 2024-02-27 | 华中科技大学 | Wind power prediction method based on combination of transfer learning and deep learning |
| CN114330935A (en) * | 2022-03-10 | 2022-04-12 | 南方电网数字电网研究院有限公司 | New energy power prediction method and system based on multiple combined strategy integrated learning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112633632A (en) | Integrated short-term wind power cluster power prediction method based on signal decomposition technology | |
| CN112348292B (en) | Short-term wind power prediction method and system based on deep learning network | |
| CN104978608B (en) | A kind of wind electric powder prediction device and prediction technique | |
| CN106228278A (en) | Photovoltaic power prognoses system | |
| CN103870923B (en) | The wind energy turbine set group of planes polymerization of coagulation type hierarchical clustering algorithm based on comentropy | |
| CN110264002B (en) | Wind power plant micro-siting scheme evaluation method based on cluster analysis | |
| CN103942736B (en) | A kind of wind power plant multimachine equivalent modeling method | |
| CN111260154B (en) | Short-term solar radiation prediction method and device based on CNN-LSTM | |
| CN110991737A (en) | Ultra-short-term wind power prediction method based on deep belief network | |
| CN113935237A (en) | Power transmission line fault type distinguishing method and system based on capsule network | |
| Syu et al. | Ultra-short-term wind speed forecasting for wind power based on gated recurrent unit | |
| CN112862274A (en) | WRF-LES and Deepar combined wind power prediction method | |
| CN104978605A (en) | Large-scale wind power prediction system and method based on deep learning network | |
| CN112836876A (en) | Power distribution network line load prediction method based on deep learning | |
| CN115689055A (en) | Short-term solar irradiance prediction method and device | |
| CN114021818A (en) | Wind power multistep prediction method considering space-time distribution characteristics | |
| CN114298132A (en) | Wind power prediction method and device and electronic equipment | |
| CN108694475B (en) | Short-time-scale photovoltaic cell power generation capacity prediction method based on hybrid model | |
| Zhang et al. | Joint forecasting of regional wind and solar power based on attention neural network | |
| CN113610285A (en) | Power prediction method for distributed wind power | |
| CN109615142A (en) | A kind of wind farm wind velocity combination forecasting method based on wavelet analysis | |
| CN110059972B (en) | Daily solar radiation resource assessment method based on functional deep belief network | |
| CN116523145A (en) | Photovoltaic power ultra-short-term prediction method and device, computer equipment and storage medium | |
| CN110717623A (en) | Photovoltaic power generation power prediction method, device and equipment integrating multiple weather conditions | |
| CN107918920B (en) | Output correlation analysis method for multiple photovoltaic power stations |
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 | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20210409 |
|
| WW01 | Invention patent application withdrawn after publication |