CN113570132A - Wind power prediction method for space-time meteorological feature extraction and deep learning - Google Patents
Wind power prediction method for space-time meteorological feature extraction and deep learning Download PDFInfo
- Publication number
- CN113570132A CN113570132A CN202110838338.4A CN202110838338A CN113570132A CN 113570132 A CN113570132 A CN 113570132A CN 202110838338 A CN202110838338 A CN 202110838338A CN 113570132 A CN113570132 A CN 113570132A
- Authority
- CN
- China
- Prior art keywords
- data
- deep learning
- space
- level
- cluster
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 25
- 238000013135 deep learning Methods 0.000 title claims abstract description 12
- 238000000605 extraction Methods 0.000 title claims description 16
- 238000013136 deep learning model Methods 0.000 claims abstract description 23
- 239000002131 composite material Substances 0.000 claims abstract description 9
- 238000007418 data mining Methods 0.000 claims abstract description 8
- 238000013507 mapping Methods 0.000 claims abstract description 7
- 238000000354 decomposition reaction Methods 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 6
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 230000006870 function Effects 0.000 claims description 3
- 230000003287 optical effect Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 claims description 3
- 238000012847 principal component analysis method Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 230000008569 process Effects 0.000 abstract description 2
- 238000013528 artificial neural network Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 238000010248 power generation Methods 0.000 description 3
- 230000009471 action Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
- 238000013526 transfer learning Methods 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
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
- G06F18/2135—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods based on approximation criteria, e.g. principal component analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- 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
Abstract
The invention discloses a wind power prediction method for extracting space-time meteorological features and deep learning, which is characterized by firstly researching the cross-correlation characteristics of the output of a new energy field station and the weather process based on wide-area space-time meteorological data and power data, establishing multi-level sub-region division based on different indexes, then establishing a high-dimensional candidate feature library based on multi-dimensional meteorological data, establishing composite meteorological features based on data mining, finally establishing a deep learning model library oriented to multi-levels based on high-dimensional depth feature mapping and high-dimensional depth data mining based on massive samples and optimized core features, and selecting an optimal model to perform cluster power prediction. By the method, the wind power is predicted under the time-space composite data, an effective matching relation is established between the time domain data and the space data, and the method has popularization value.
Description
Technical Field
The invention relates to a wind power prediction method for space-time meteorological feature extraction and deep learning, and belongs to the field of new energy power prediction.
Background
The wind resource has typical volatility and randomness natural characteristics, which are reflected by the comprehensive effect of various factors of meteorological factors and landforms; the wind power generation system is driven by wind resources and further influenced by a wind power generation conversion rule, the time characteristics of the wind power also have certain volatility and randomness, and along with the change of the spatial scale, the time characteristics and the volatility of the spatial characteristics of different wind powers can be superposed to show different characteristics. The control of the power generation time, the spatial fluctuation and the change rule thereof is a necessary premise for improving the power prediction result and improving the system precision, safety and economy.
The wind power plant power fluctuation is a result of combined action of consistency and difference of meteorological parameters, so when the power of regional wind power plant groups is subjected to centralized prediction, trends and differences of the meteorological parameters corresponding to different spatial positions need to be considered. However, for the artificial neural network, too many input parameters inevitably lead to the complication of the network structure, and further, the artificial neural network is easy to fall into a local extremum in the training process, so that the convergence speed of the algorithm is slow or even the algorithm cannot be converged. Therefore, when the artificial neural network is adopted for wind power cluster modeling, the feature extraction of the spatial meteorological parameters is the key for ensuring the prediction effect.
By constructing the multi-level depth cluster power prediction method for extracting the composite spatio-temporal meteorological features, not only can the power be predicted based on the time and space factors, but also the accuracy of the result is improved, the redundancy of the predicted data can be reduced, and the power prediction rate is improved.
Disclosure of Invention
The invention aims to provide a wind power prediction method for space-time meteorological feature extraction and deep learning, which aims to solve the problems in the background technology, can not only predict power based on time and space factors and improve the accuracy of results, but also reduce the redundancy of predicted data and improve the power prediction rate.
The purpose of the invention is realized by the following technical measures:
a wind power prediction method for space-time meteorological feature extraction and deep learning is characterized by comprising the following steps:
s1: carrying out hierarchical data retrieval on the collected data with different longitudes and latitudes, carrying out cluster data division according to dynamic self-adaptive selection of space-time resources, and constructing multi-hierarchical new energy sub-regions with different indexes as bases;
s2: according to the new energy multi-dimensional data characteristics, performing different characteristic decomposition on the original region data to construct a sub-region composite characteristic library, performing characteristic optimization on the basis of the composite meteorological characteristics mined by the data, and selecting effective characteristics;
s3: and (3) carrying out data resource matching on the 24h data, the 48h data, the 72h data and the 96h data collected in the step (S1.3) and the optimized effective features, putting the data of the multi-level new energy sub-region into a deep learning model library based on high-dimensional depth feature mapping and high-dimensional depth data mining, carrying out power prediction facing to a multi-level new energy wind/light cluster, selecting meteorological data to be put into the deep learning model for suitability evaluation, and selecting an optimal deep learning model as a final level power prediction model.
Further, the specific step of S1 includes:
s1.1: selecting mass data of n wind power plants and m optical power plants with the same total installed capacity in the same longitude and latitude area;
s1.2: carrying out spatial region layering on the mass data acquired in the step S1.1 through space-time resource dynamic self-adaptive selection based on cluster clustering division, making a topological structure on the selected data of the wind/light power plant according to a geographic space, dividing the data into a hierarchical data structure from provincial level to regional level according to the administrative region level of the geographic region, and sequentially obtaining hierarchical 1 data, hierarchical 2 data and hierarchical n data;
s1.3: performing time scale judgment on the level 1 data, the level 2 data to the level n data in the step S1.2 through space-time resource dynamic self-adaptive selection based on cluster clustering division, dividing the data into 24h data, 48h data, 72h data and 96h data with similar calendar history power, wherein the smaller the time scale, the larger the weight distributed in power prediction;
s1.4: and (2) considering the influence of the topographic features and the climatic features of the new energy station, extracting the features of the 24h data, the 48h data, the 72h data and the 96h data collected in the step S1.3, performing correlation analysis on the extracted features, dividing all the extracted features into a plurality of clusters by adopting a cluster analysis method on the basis of a historical power data sequence of the new energy station, and then adjusting the divided clusters by considering the topological structure of a power grid to ensure the integrity of the clusters, so that the optimal cluster division with the minimum granularity is realized, and the multi-level new energy sub-region is obtained.
Further, the specific step of S2 includes:
s2.1: performing feature extraction on the original mass data of the region acquired in the step S1.1 by adopting a principal component analysis method, and performing frequency domain feature decomposition, time sequence feature decomposition and spatial feature decomposition on the feature data;
s2.2: dividing the decomposed data characteristics into statistical characteristics, fluctuation sequence characteristics and function transformation characteristics, and constructing a multi-dimensional meteorological and power data characteristic database;
s2.3: constructing the average value, mode, quantiles and range statistical characteristics of each sub-cluster aiming at the extracted characteristics of each sub-cluster based on the gridding numerical weather forecast and cluster division results, calculating mutual information among data through a maximum correlation minimum redundancy algorithm of the mutual information, performing characteristic selection on a high-dimensional characteristic library according to maximum correlation and minimum redundancy sorting, and selecting some most effective characteristics from original characteristics;
s2.4: and determining the number of the optimal features of the data and the combination of the optimal features through multiple prediction results.
Further, the specific step of S3 includes:
s3.1, performing data resource matching on the 24h data, the 48h data, the 72h data and the 96h data which are acquired in the step S1.3 and the optimized effective characteristics in the step S2.4;
s3.2: based on high-dimensional depth feature mapping and high-dimensional depth data mining, putting data of the multi-level new energy sub-region into a deep learning model library, and performing power prediction facing a multi-level new energy wind/light cluster;
and S3.3, performing applicability evaluation on the deep learning model by referring to errors among the deep learning models in the data of the historical resource library, and selecting the optimal deep learning model as a final level power prediction model.
The invention achieves the following beneficial effects: through the multi-level division of data, the fluctuation and the change rule of the output of the new energy station are mastered, and the precision, the safety and the economy of system operation planning are effectively improved. Through data feature extraction, parameter input can be reduced, convergence rate is improved, the situation of falling into a local extreme value is effectively reduced and avoided, accuracy and stability of a prediction result are improved through deep learning model construction, running cost of a power grid is reduced, wind power plant short-term power prediction method based on feature selection and multi-level deep transfer learning is comprehensively used, accuracy of the prediction model can be effectively improved, and the wind power prediction method has an important effect on wind power prediction.
Drawings
Fig. 1 is a block diagram of the overall flow structure of the present invention.
Detailed Description
The following detailed description is made with reference to the accompanying drawings in the embodiment of the invention, and the purpose of the invention is to provide a wind power prediction method for space-time meteorological feature extraction and deep learning.
As shown in fig. 1, a wind power prediction method for space-time meteorological feature extraction and deep learning includes the following steps:
s1: carrying out hierarchical data retrieval on the collected data with different longitudes and latitudes, carrying out cluster data division according to dynamic self-adaptive selection of space-time resources, and constructing multi-hierarchical new energy sub-regions with different indexes as bases; the method comprises the following specific steps:
s1.1: selecting mass data of n wind power plants and m optical power plants with the same total installed capacity in the same longitude and latitude area;
s1.2: carrying out spatial region layering on the mass data acquired in the step S1.1 through space-time resource dynamic self-adaptive selection based on cluster clustering division, making a topological structure on the selected data of the wind/light power plant according to a geographic space, dividing the data into a hierarchical data structure from provincial level to regional level according to the administrative region level of the geographic region, and sequentially obtaining hierarchical 1 data, hierarchical 2 data and hierarchical n data;
s1.3: performing time scale judgment on the level 1 data, the level 2 data to the level n data in the step S1.2 through space-time resource dynamic self-adaptive selection based on cluster clustering division, dividing the data into 24h data, 48h data, 72h data and 96h data with similar calendar history power, wherein the smaller the time scale, the larger the weight distributed in power prediction;
s1.4: and (2) considering the influence of the topographic features and the climatic features of the new energy station, extracting the features of the 24h data, the 48h data, the 72h data and the 96h data collected in the step S1.3, performing correlation analysis on the extracted features, dividing all the extracted features into a plurality of clusters by adopting a cluster analysis method on the basis of a historical power data sequence of the new energy station, and then adjusting the divided clusters by considering the topological structure of a power grid to ensure the integrity of the clusters, so that the optimal cluster division with the minimum granularity is realized, and the multi-level new energy sub-region is obtained.
S2: s2: according to the new energy multi-dimensional data characteristics, performing different characteristic decomposition on the original region data to construct a sub-region composite characteristic library, performing characteristic optimization on the basis of the composite meteorological characteristics mined by the data, and selecting effective characteristics; the method comprises the following specific steps:
s2.1: performing feature extraction on the original mass data of the region acquired in the step S1.1 by adopting a principal component analysis method, and performing frequency domain feature decomposition, time sequence feature decomposition and spatial feature decomposition on the feature data;
s2.2: dividing the decomposed data characteristics into statistical characteristics, fluctuation sequence characteristics and function transformation characteristics, and constructing a multi-dimensional meteorological and power data characteristic database;
s2.3: constructing the average value, mode, quantiles and range statistical characteristics of each sub-cluster aiming at the extracted characteristics of each sub-cluster based on the gridding numerical weather forecast and cluster division results, calculating mutual information among data through a maximum correlation minimum redundancy algorithm of the mutual information, performing characteristic selection on a high-dimensional characteristic library according to maximum correlation and minimum redundancy sorting, and selecting some most effective characteristics from original characteristics;
s2.4: and determining the number of the optimal features of the data and the combination of the optimal features through multiple prediction results.
S3: performing data resource matching on the 24h data, 48h data, 72h data and 96h data collected in the step S1.3 and the optimized effective features, putting data of a multi-level new energy sub-region into a deep learning model library based on high-dimensional depth feature mapping and high-dimensional depth data mining, performing power prediction facing a multi-level new energy wind/light cluster, selecting meteorological data to be put into the deep learning model for suitability evaluation, and selecting an optimal deep learning model as a final level power prediction model; the method comprises the following specific steps:
s3.1, performing data resource matching on the 24h data, the 48h data, the 72h data and the 96h data which are acquired in the step S1.3 and the optimized effective characteristics in the step S2.4;
s3.2: based on high-dimensional depth feature mapping and high-dimensional depth data mining, putting data of the multi-level new energy sub-region into a deep learning model library, and performing power prediction facing a multi-level new energy wind/light cluster;
and S3.3, performing applicability evaluation on the deep learning model by referring to errors among the deep learning models in the data of the historical resource library, and selecting the optimal deep learning model as a final level power prediction model.
Those not described in detail in this specification are within the skill of the art.
Claims (4)
1. A wind power prediction method for space-time meteorological feature extraction and deep learning is characterized by comprising the following steps:
s1: carrying out hierarchical data retrieval on the collected data with different longitudes and latitudes, carrying out cluster data division according to dynamic self-adaptive selection of space-time resources, and constructing multi-hierarchical new energy sub-regions with different indexes as bases;
s2: according to the new energy multi-dimensional data characteristics, performing different characteristic decomposition on the original region data to construct a sub-region composite characteristic library, performing characteristic optimization on the basis of the composite meteorological characteristics mined by the data, and selecting effective characteristics;
s3: and (3) carrying out data resource matching on the 24h data, the 48h data, the 72h data and the 96h data collected in the step (S1.3) and the optimized effective features, putting the data of the multi-level new energy sub-region into a deep learning model library based on high-dimensional depth feature mapping and high-dimensional depth data mining, carrying out power prediction facing to a multi-level new energy wind/light cluster, selecting meteorological data to be put into the deep learning model for suitability evaluation, and selecting an optimal deep learning model as a final level power prediction model.
2. The method for predicting wind power through space-time meteorological feature extraction and deep learning according to claim 1, wherein the step S1 specifically comprises:
s1.1: selecting mass data of n wind power plants and m optical power plants with the same total installed capacity in the same longitude and latitude area;
s1.2: carrying out spatial region layering on the mass data acquired in the step S1.1 through space-time resource dynamic self-adaptive selection based on cluster clustering division, making a topological structure on the selected data of the wind/light power plant according to a geographic space, dividing the data into a hierarchical data structure from provincial level to regional level according to the administrative region level of the geographic region, and sequentially obtaining hierarchical 1 data, hierarchical 2 data and hierarchical n data;
s1.3: performing time scale judgment on the level 1 data, the level 2 data to the level n data in the step S1.2 through space-time resource dynamic self-adaptive selection based on cluster clustering division, dividing the data into 24h data, 48h data, 72h data and 96h data with similar calendar history power, wherein the smaller the time scale, the larger the weight distributed in power prediction;
s1.4: and (2) considering the influence of the topographic features and the climatic features of the new energy station, extracting the features of the 24h data, the 48h data, the 72h data and the 96h data collected in the step S1.3, performing correlation analysis on the extracted features, dividing all the extracted features into a plurality of clusters by adopting a cluster analysis method on the basis of a historical power data sequence of the new energy station, and then adjusting the divided clusters by considering the topological structure of a power grid to ensure the integrity of the clusters, so that the optimal cluster division with the minimum granularity is realized, and the multi-level new energy sub-region is obtained.
3. The method for predicting wind power through space-time meteorological feature extraction and deep learning according to claim 2, wherein the step S2 specifically comprises:
s2.1: performing feature extraction on the original mass data of the region acquired in the step S1.1 by adopting a principal component analysis method, and performing frequency domain feature decomposition, time sequence feature decomposition and spatial feature decomposition on the feature data;
s2.2: dividing the decomposed data characteristics into statistical characteristics, fluctuation sequence characteristics and function transformation characteristics, and constructing a multi-dimensional meteorological and power data characteristic database;
s2.3: constructing the average value, mode, quantiles and range statistical characteristics of each sub-cluster aiming at the extracted characteristics of each sub-cluster based on the gridding numerical weather forecast and cluster division results, calculating mutual information among data through a maximum correlation minimum redundancy algorithm of the mutual information, performing characteristic selection on a high-dimensional characteristic library according to maximum correlation and minimum redundancy sorting, and selecting some most effective characteristics from original characteristics;
s2.4: and determining the number of the optimal features of the data and the combination of the optimal features through multiple prediction results.
4. The method for predicting wind power through space-time meteorological feature extraction and deep learning according to claim 3, wherein the step S3 specifically comprises the steps of:
s3.1, performing data resource matching on the 24h data, the 48h data, the 72h data and the 96h data which are acquired in the step S1.3 and the optimized effective characteristics in the step S2.4;
s3.2: based on high-dimensional depth feature mapping and high-dimensional depth data mining, putting data of the multi-level new energy sub-region into a deep learning model library, and performing power prediction facing a multi-level new energy wind/light cluster;
and S3.3, performing applicability evaluation on the deep learning model by referring to errors among the deep learning models in the data of the historical resource library, and selecting the optimal deep learning model as a final level power prediction model.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110838338.4A CN113570132A (en) | 2021-07-23 | 2021-07-23 | Wind power prediction method for space-time meteorological feature extraction and deep learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110838338.4A CN113570132A (en) | 2021-07-23 | 2021-07-23 | Wind power prediction method for space-time meteorological feature extraction and deep learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN113570132A true CN113570132A (en) | 2021-10-29 |
Family
ID=78166882
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110838338.4A Pending CN113570132A (en) | 2021-07-23 | 2021-07-23 | Wind power prediction method for space-time meteorological feature extraction and deep learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113570132A (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114266421A (en) * | 2022-03-01 | 2022-04-01 | 南方电网数字电网研究院有限公司 | New energy power prediction method based on composite meteorological feature construction and selection |
CN116488158A (en) * | 2023-04-24 | 2023-07-25 | 国能日新科技股份有限公司 | Method and device for predicting medium-long-term electric quantity of wind power based on transfer learning |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106849066A (en) * | 2017-03-07 | 2017-06-13 | 云南电网有限责任公司电力科学研究院 | A kind of regional wind power prediction method |
CN111753893A (en) * | 2020-06-12 | 2020-10-09 | 国网福建省电力有限公司 | Wind turbine generator power cluster prediction method based on clustering and deep learning |
CN112949904A (en) * | 2021-01-28 | 2021-06-11 | 华中科技大学 | Wind power plant short-term power prediction method based on feature selection and multi-level deep transfer learning |
-
2021
- 2021-07-23 CN CN202110838338.4A patent/CN113570132A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106849066A (en) * | 2017-03-07 | 2017-06-13 | 云南电网有限责任公司电力科学研究院 | A kind of regional wind power prediction method |
CN111753893A (en) * | 2020-06-12 | 2020-10-09 | 国网福建省电力有限公司 | Wind turbine generator power cluster prediction method based on clustering and deep learning |
CN112949904A (en) * | 2021-01-28 | 2021-06-11 | 华中科技大学 | Wind power plant short-term power prediction method based on feature selection and multi-level deep transfer learning |
Non-Patent Citations (1)
Title |
---|
杨子民等: "基于集群动态划分与BLSTM深度学习的风电集群短期功率预测", 高电压技术, vol. 47, no. 4, 30 April 2021 (2021-04-30), pages 1195 - 1203 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114266421A (en) * | 2022-03-01 | 2022-04-01 | 南方电网数字电网研究院有限公司 | New energy power prediction method based on composite meteorological feature construction and selection |
CN114266421B (en) * | 2022-03-01 | 2022-08-09 | 南方电网数字电网研究院有限公司 | New energy power prediction method based on composite meteorological feature construction and selection |
CN116488158A (en) * | 2023-04-24 | 2023-07-25 | 国能日新科技股份有限公司 | Method and device for predicting medium-long-term electric quantity of wind power based on transfer learning |
CN116488158B (en) * | 2023-04-24 | 2023-09-15 | 国能日新科技股份有限公司 | Method and device for predicting medium-long-term electric quantity of wind power based on transfer learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113962364B (en) | Multi-factor power load prediction method based on deep learning | |
CN103268366A (en) | Combined wind power prediction method suitable for distributed wind power plant | |
CN102411729B (en) | Wind power prediction method based on adaptive linear logic network | |
CN104715292A (en) | City short-term water consumption prediction method based on least square support vector machine model | |
CN113570132A (en) | Wind power prediction method for space-time meteorological feature extraction and deep learning | |
CN117236199B (en) | Method and system for improving water quality and guaranteeing water safety of river and lake in urban water network area | |
CN112116130B (en) | Short-term scheduling rule extraction method based on variable structure deep learning framework | |
Adedeji et al. | Hybrid neurofuzzy wind power forecast and wind turbine location for embedded generation | |
CN108596242A (en) | Power grid meteorology load forecasting method based on wavelet neural network and support vector machines | |
CN113554466A (en) | Short-term power consumption prediction model construction method, prediction method and device | |
CN111695666A (en) | Wind power ultra-short term conditional probability prediction method based on deep learning | |
CN111199298A (en) | Flood forecasting method and system based on neural network | |
CN111260206A (en) | Photovoltaic power generation influence factor evaluation model, construction method and application | |
Yu et al. | Ultra-short-term wind power subsection forecasting method based on extreme weather | |
CN117556197A (en) | Typhoon vortex initialization method based on artificial intelligence | |
CN116485582A (en) | Heat supply optimization regulation and control method and device based on deep learning | |
CN113780679B (en) | Load prediction method and device based on ubiquitous power Internet of things | |
CN108615091A (en) | Electric power meteorology load data prediction technique based on cluster screening and neural network | |
CN114862007A (en) | Short-period gas production rate prediction method and system for carbonate gas well | |
CN108596781A (en) | A kind of electric power system data excavates and prediction integration method | |
CN114372615A (en) | Short-term photovoltaic power prediction method and system considering spatial correlation | |
Xiao et al. | Research on fault-environment association rules of distribution network based on improved Apriori algorithm | |
CN113792919A (en) | Wind power prediction method based on combination of transfer learning and deep learning | |
Lawan et al. | ANN and GIS-assisted methodology for wind resource assessment (WRA) in Sarawak | |
Bâra et al. | Intelligent systems for predicting and analyzing data in power grid companies |
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 |