Comparison of ultra-short-term forecast curves.
<div><p>Wind power forecasting has complex nonlinear features and behavioral patterns across time scales, which is a severe test for traditional forecasting techniques. To address the multi-scale problem in wind power forecasting, this paper innovatively proposes an ultra-short-term fore...
محفوظ في:
| المؤلف الرئيسي: | |
|---|---|
| مؤلفون آخرون: | , |
| منشور في: |
2024
|
| الموضوعات: | |
| الوسوم: |
إضافة وسم
لا توجد وسوم, كن أول من يضع وسما على هذه التسجيلة!
|
| _version_ | 1852025666844753920 |
|---|---|
| author | Dongjin Ma (19949668) |
| author2 | Yingcai Gao (19949671) Qin Dai (177488) |
| author2_role | author author |
| author_facet | Dongjin Ma (19949668) Yingcai Gao (19949671) Qin Dai (177488) |
| author_role | author |
| dc.creator.none.fl_str_mv | Dongjin Ma (19949668) Yingcai Gao (19949671) Qin Dai (177488) |
| dc.date.none.fl_str_mv | 2024-10-25T17:22:47Z |
| dc.identifier.none.fl_str_mv | 10.1371/journal.pone.0309676.g010 |
| dc.relation.none.fl_str_mv | https://figshare.com/articles/figure/Comparison_of_ultra-short-term_forecast_curves_/27305161 |
| dc.rights.none.fl_str_mv | CC BY 4.0 info:eu-repo/semantics/openAccess |
| dc.subject.none.fl_str_mv | Genetics Biotechnology Ecology Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified traditional forecasting techniques rank approximation method paper innovatively proposes overall operational efficiency complex nonlinear features bounded dimensional space wind power system wind power forecasting wind power enterprises scale mixing mechanism improved transformer model term prediction scenario existing prediction methods experimental results show devlin normalization method power grid scale problem model realizes prediction accuracy stable operation severe test research results original data obvious advantages multilayer perceptron internet access input sequences important information historical data firstly focuses feature selection decoder architecture data sequence also help |
| dc.title.none.fl_str_mv | Comparison of ultra-short-term forecast curves. |
| dc.type.none.fl_str_mv | Image Figure info:eu-repo/semantics/publishedVersion image |
| description | <div><p>Wind power forecasting has complex nonlinear features and behavioral patterns across time scales, which is a severe test for traditional forecasting techniques. To address the multi-scale problem in wind power forecasting, this paper innovatively proposes an ultra-short-term forecasting model LFformer based on Legendre-Fourier, which firstly focuses on the important information in the input sequences by using the encoder-decoder architecture, and then scales the range of the original data with the Devlin normalization method, and then utilizes the Legendre polynomials to The data sequence is projected into a bounded dimensional space, the historical data is compressed using feature representation, then feature selection is performed using the low-rank approximation method of Fourier Transform, the prediction is inputted into the multilayer perceptron through the multi-scale mixing mechanism, and finally the results are outputted after back-normalization. The experimental results show that compared with the existing prediction methods, the model realizes the improvement of prediction accuracy and stability, especially in the ultra-short-term prediction scenario, with obvious advantages. The research results are not only valuable for improving the overall operational efficiency of the wind power system, but also help to enhance the stable operation of the power grid, which provides strong technical support and guarantee for wind power enterprises to improve the competitiveness of bidding for Internet access in the power market competition.</p></div> |
| eu_rights_str_mv | openAccess |
| id | Manara_4f39d3dcbc84a7dbbabf3542e0bd3fe5 |
| identifier_str_mv | 10.1371/journal.pone.0309676.g010 |
| network_acronym_str | Manara |
| network_name_str | ManaraRepo |
| oai_identifier_str | oai:figshare.com:article/27305161 |
| publishDate | 2024 |
| repository.mail.fl_str_mv | |
| repository.name.fl_str_mv | |
| repository_id_str | |
| rights_invalid_str_mv | CC BY 4.0 |
| spelling | Comparison of ultra-short-term forecast curves.Dongjin Ma (19949668)Yingcai Gao (19949671)Qin Dai (177488)GeneticsBiotechnologyEcologyBiological Sciences not elsewhere classifiedMathematical Sciences not elsewhere classifiedInformation Systems not elsewhere classifiedtraditional forecasting techniquesrank approximation methodpaper innovatively proposesoverall operational efficiencycomplex nonlinear featuresbounded dimensional spacewind power systemwind power forecastingwind power enterprisesscale mixing mechanismimproved transformer modelterm prediction scenarioexisting prediction methodsexperimental results showdevlin normalization methodpower gridscale problemmodel realizesprediction accuracystable operationsevere testresearch resultsoriginal dataobvious advantagesmultilayer perceptroninternet accessinput sequencesimportant informationhistorical datafirstly focusesfeature selectiondecoder architecturedata sequencealso help<div><p>Wind power forecasting has complex nonlinear features and behavioral patterns across time scales, which is a severe test for traditional forecasting techniques. To address the multi-scale problem in wind power forecasting, this paper innovatively proposes an ultra-short-term forecasting model LFformer based on Legendre-Fourier, which firstly focuses on the important information in the input sequences by using the encoder-decoder architecture, and then scales the range of the original data with the Devlin normalization method, and then utilizes the Legendre polynomials to The data sequence is projected into a bounded dimensional space, the historical data is compressed using feature representation, then feature selection is performed using the low-rank approximation method of Fourier Transform, the prediction is inputted into the multilayer perceptron through the multi-scale mixing mechanism, and finally the results are outputted after back-normalization. The experimental results show that compared with the existing prediction methods, the model realizes the improvement of prediction accuracy and stability, especially in the ultra-short-term prediction scenario, with obvious advantages. The research results are not only valuable for improving the overall operational efficiency of the wind power system, but also help to enhance the stable operation of the power grid, which provides strong technical support and guarantee for wind power enterprises to improve the competitiveness of bidding for Internet access in the power market competition.</p></div>2024-10-25T17:22:47ZImageFigureinfo:eu-repo/semantics/publishedVersionimage10.1371/journal.pone.0309676.g010https://figshare.com/articles/figure/Comparison_of_ultra-short-term_forecast_curves_/27305161CC BY 4.0info:eu-repo/semantics/openAccessoai:figshare.com:article/273051612024-10-25T17:22:47Z |
| spellingShingle | Comparison of ultra-short-term forecast curves. Dongjin Ma (19949668) Genetics Biotechnology Ecology Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified traditional forecasting techniques rank approximation method paper innovatively proposes overall operational efficiency complex nonlinear features bounded dimensional space wind power system wind power forecasting wind power enterprises scale mixing mechanism improved transformer model term prediction scenario existing prediction methods experimental results show devlin normalization method power grid scale problem model realizes prediction accuracy stable operation severe test research results original data obvious advantages multilayer perceptron internet access input sequences important information historical data firstly focuses feature selection decoder architecture data sequence also help |
| status_str | publishedVersion |
| title | Comparison of ultra-short-term forecast curves. |
| title_full | Comparison of ultra-short-term forecast curves. |
| title_fullStr | Comparison of ultra-short-term forecast curves. |
| title_full_unstemmed | Comparison of ultra-short-term forecast curves. |
| title_short | Comparison of ultra-short-term forecast curves. |
| title_sort | Comparison of ultra-short-term forecast curves. |
| topic | Genetics Biotechnology Ecology Biological Sciences not elsewhere classified Mathematical Sciences not elsewhere classified Information Systems not elsewhere classified traditional forecasting techniques rank approximation method paper innovatively proposes overall operational efficiency complex nonlinear features bounded dimensional space wind power system wind power forecasting wind power enterprises scale mixing mechanism improved transformer model term prediction scenario existing prediction methods experimental results show devlin normalization method power grid scale problem model realizes prediction accuracy stable operation severe test research results original data obvious advantages multilayer perceptron internet access input sequences important information historical data firstly focuses feature selection decoder architecture data sequence also help |