融合深度误差反馈学习和注意力机制的短期风电功率预测
为提高风电功率预测精度,提出了一种有机融合深度反馈学习与注意力机制的短期风电功率预测方法.首先,以风电场数值天气预报(numerical weather prediction,NWP)为原始输入,基于双层长短期记忆网络(long short-term memory,LSTM)模型对风电功率进行初步预测.其次,利用极端梯度提升(eXtreme gradient boosting,XGBoost)算法构建误差估计模型,以便在给定未来一段时间内 NWP 数据的情况下对初步预测误差进行快速估计.然后,利用自适应白噪声完备集成经验模态分解法(complete ensemble empirical mod...
Saved in:
| Published in | 电力系统保护与控制 Vol. 52; no. 4; pp. 100 - 108 |
|---|---|
| Main Authors | , , , , , , |
| Format | Journal Article |
| Language | Chinese |
| Published |
湖南大学电气与信息工程学院,湖南 长沙 410082
16.02.2024
|
| Subjects | |
| Online Access | Get full text |
| ISSN | 1674-3415 |
| DOI | 10.19783/j.cnki.pspc.230914 |
Cover
| Abstract | 为提高风电功率预测精度,提出了一种有机融合深度反馈学习与注意力机制的短期风电功率预测方法.首先,以风电场数值天气预报(numerical weather prediction,NWP)为原始输入,基于双层长短期记忆网络(long short-term memory,LSTM)模型对风电功率进行初步预测.其次,利用极端梯度提升(eXtreme gradient boosting,XGBoost)算法构建误差估计模型,以便在给定未来一段时间内 NWP 数据的情况下对初步预测误差进行快速估计.然后,利用自适应白噪声完备集成经验模态分解法(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)将初步预测误差分解为不同频段的误差序列,并将其作为附加性反馈输入,对风电功率进行二次预测.进一步在二次预测模型中引入注意力机制,为风电功率预测序列与误差序列动态分配权重,由此引导预测模型在学习过程中充分挖掘学习与误差相关的关键特征.最后,仿真结果表明所提方法可显著提高短期风电功率预测的可靠性. |
|---|---|
| AbstractList | 为提高风电功率预测精度,提出了一种有机融合深度反馈学习与注意力机制的短期风电功率预测方法.首先,以风电场数值天气预报(numerical weather prediction,NWP)为原始输入,基于双层长短期记忆网络(long short-term memory,LSTM)模型对风电功率进行初步预测.其次,利用极端梯度提升(eXtreme gradient boosting,XGBoost)算法构建误差估计模型,以便在给定未来一段时间内 NWP 数据的情况下对初步预测误差进行快速估计.然后,利用自适应白噪声完备集成经验模态分解法(complete ensemble empirical mode decomposition with adaptive noise,CEEMDAN)将初步预测误差分解为不同频段的误差序列,并将其作为附加性反馈输入,对风电功率进行二次预测.进一步在二次预测模型中引入注意力机制,为风电功率预测序列与误差序列动态分配权重,由此引导预测模型在学习过程中充分挖掘学习与误差相关的关键特征.最后,仿真结果表明所提方法可显著提高短期风电功率预测的可靠性. |
| Abstract_FL | To enhance the accuracy of wind power forecasting,a short-term wind power forecasting method is proposed,one that synergistically integrates deep feedback learning with attention mechanisms.First,the historical data of numerical weather prediction(NWP)from the wind farm is taken as the original input.A dual-layer long short-term memory(LSTM)-based learning model is used for the preliminary prediction of wind power.Next,an error estimation model is established based on an extreme gradient boosting(XGBoost)algorithm.This enables fast estimation of the initial prediction errors given the future NWP data.Then,complete ensemble empirical mode decomposition with adaptive noise(CEEMDAN)is used to decompose the initial prediction errors into error sequences of different frequency bands.These serve as an additional feedback input for the secondary prediction of wind power.Also,an attention mechanism is introduced into the secondary prediction model to dynamically allocate weights to the wind power forecasting and error sequences and thereby instructing the prediction model to fully mine and learn the key features related to the prediction errors during the learning process.Finally,the simulation results indicate that the proposed method can remarkably enhance the reliability of short-term wind power forecasting. |
| Author | 李杨 曾杨 朱利鹏 胡宇晗 李佳勇 郑李梦千 帅智康 |
| AuthorAffiliation | 湖南大学电气与信息工程学院,湖南 长沙 410082 |
| AuthorAffiliation_xml | – name: 湖南大学电气与信息工程学院,湖南 长沙 410082 |
| Author_FL | SHUAI Zhikang ZHENG Limengqian ZENG Yang HU Yuhan ZHU Lipeng LI Yang LI Jiayong |
| Author_FL_xml | – sequence: 1 fullname: HU Yuhan – sequence: 2 fullname: ZHU Lipeng – sequence: 3 fullname: LI Jiayong – sequence: 4 fullname: LI Yang – sequence: 5 fullname: ZENG Yang – sequence: 6 fullname: ZHENG Limengqian – sequence: 7 fullname: SHUAI Zhikang |
| Author_xml | – sequence: 1 fullname: 胡宇晗 – sequence: 2 fullname: 朱利鹏 – sequence: 3 fullname: 李佳勇 – sequence: 4 fullname: 李杨 – sequence: 5 fullname: 曾杨 – sequence: 6 fullname: 郑李梦千 – sequence: 7 fullname: 帅智康 |
| BookMark | eNotzctKw0AYQOFZVLDWPoFbt4n_ZJKZzFKKNyy46b4kMxNplLQaxBcoWKq9IK60GFEIbmoRqcU-j5O0b6Ggq7P7zhoqRM1IIbSBwcScuWQrNEV00jBbcUuYFgGO7QIqYspsg9jYWUXlOG74AAQ7DnV5ER0uHnt62Mlm73qeLiYTPXvTg94y7ehx-v31pG9vso_XrD3Q3YdsNNedz_y-nSfjbJQsX_r53VR3k7x_tXxuZ9PrdbQSeKexKv-3hGq7O7XKvlE92juobFeNmHMwOPd8CRhLzIRrOcTyAp8QFlAlqS-lC7ZQgmJQgeSOwIoBDZhQFFwCwFxGSmjzj730osCLjuth8-I8-h3WQ3lmgWWDDRjID-2Wa7s |
| ContentType | Journal Article |
| Copyright | Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| Copyright_xml | – notice: Copyright © Wanfang Data Co. Ltd. All Rights Reserved. |
| DBID | 2B. 4A8 92I 93N PSX TCJ |
| DOI | 10.19783/j.cnki.pspc.230914 |
| DatabaseName | Wanfang Data Journals - Hong Kong WANFANG Data Centre Wanfang Data Journals 万方数据期刊 - 香港版 China Online Journals (COJ) China Online Journals (COJ) |
| DatabaseTitleList | |
| DeliveryMethod | fulltext_linktorsrc |
| DocumentTitle_FL | Short-term wind power forecasting with the integration of a deep error feedback learning and attention mechanism |
| EndPage | 108 |
| ExternalDocumentID | jdq202404010 |
| GroupedDBID | -03 2B. 4A8 92I 93N ALMA_UNASSIGNED_HOLDINGS CCEZO CEKLB GROUPED_DOAJ PSX TCJ |
| ID | FETCH-LOGICAL-s990-99abd011d17c82532afb337f6ed6bdd804cec610efd95c1e706f7ce6083007873 |
| ISSN | 1674-3415 |
| IngestDate | Thu May 29 04:03:04 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 4 |
| Keywords | 注意力机制 deep learning LSTM feedback learning attention mechanism 风电功率预测 反馈学习 深度学习 长短时记忆单元 wind power forecasting |
| Language | Chinese |
| LinkModel | OpenURL |
| MergedId | FETCHMERGED-LOGICAL-s990-99abd011d17c82532afb337f6ed6bdd804cec610efd95c1e706f7ce6083007873 |
| PageCount | 9 |
| ParticipantIDs | wanfang_journals_jdq202404010 |
| PublicationCentury | 2000 |
| PublicationDate | 2024-02-16 |
| PublicationDateYYYYMMDD | 2024-02-16 |
| PublicationDate_xml | – month: 02 year: 2024 text: 2024-02-16 day: 16 |
| PublicationDecade | 2020 |
| PublicationTitle | 电力系统保护与控制 |
| PublicationTitle_FL | Power System Protection and Control |
| PublicationYear | 2024 |
| Publisher | 湖南大学电气与信息工程学院,湖南 长沙 410082 |
| Publisher_xml | – name: 湖南大学电气与信息工程学院,湖南 长沙 410082 |
| SSID | ssib003155689 ssib023166999 ssib002424069 ssj0002912115 ssib051374514 ssib036435463 |
| Score | 2.4640872 |
| Snippet | 为提高风电功率预测精度,提出了一种有机融合深度反馈学习与注意力机制的短期风电功率预测方法.首先,以风电场数值天气预报(numerical weather prediction,NWP)为原始输入,基于双层长短期记忆网络(long short-term... |
| SourceID | wanfang |
| SourceType | Aggregation Database |
| StartPage | 100 |
| Title | 融合深度误差反馈学习和注意力机制的短期风电功率预测 |
| URI | https://d.wanfangdata.com.cn/periodical/jdq202404010 |
| Volume | 52 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnR3JahRBtInx4kUUFbdIDtYpdOyl1mP1TA9B0VOE3EKvbjBGJ7nkHDBEk4h40mBEIXiJQSQG8z32TPIXvlfdmWmdgAsMTc3rt7-uqVc19aot6zp1UpHmrrJdF_9mpElqR3GS28rnjh8nMWc-FjjfvsOn7tKbM2xm5ESvtmtpYT6eTBaPrSv5n6gCDOKKVbL_ENk-UwBAG-ILV4gwXP8qxiSURIVENknIiHKIlCTkJBAkcBESaKI54ugWfhAiiA6xIVuGSiECUjGimwaZkgCAjmHoEdkwDH2iDWdJkRDJNVEBQlQDpSBEkgDIBVEa0bDRQp4lDrRRlk9kaG6BFHbEp4UQgEthcDxDzhFBBvXUeYgwQAjoFpSNwLAChBZRRi7gaGog0sjleNWir-3Rs4YekmCi8ZkuFQGtFVFigFKa6lbEWqGu4CnZ-gWlaQSBxCYqhrgBkeIYFNPQsr7m4lHcpl2WhJpeYrwAWnDDqAnqGAVpZUMVsL5TANnB9sBg4ws0Cyx3a08AQyqIKCg34KPQYvC-1xiWO2FuM2SH9zxAnaB4XlNtzRjrTGxIVlh90GNerXPT2gjmOk4tGXLNoRvD4ywuGJqBNmk_ejA515lLsKJAlfXAvx1g_jB9gj6E0QJLIU96QpT7Kaq1jypPxArs2kCDB-P1v8MchHM1mDf7kEbXX-PAXF9QVm0HwBTMU3hyIW5f7htfnTiGit8YVtuU7LXzqH2vll1On7FOV9PCcV328bPWyOL9c9atg3erxcvl7t6XYn_rYGen2PtcrK8ebi0X21s_vr8vXr3ofv3UXVovVt52N_aL5W-9N0u9ze3uxubhx7Xe691iZbO39uzww1J39_l5a7oVTjem7OrlJ3YHEkRbqShOYexNXZFIj_lelMe-L3KepTxOU-nQJEtg6pPlqWKJmwmH5yLJOMyoMOsX_gVrtP24nV20xl2fMpZGbqIiRiMRKXBNzqSSGc-5K6NL1lhl-2z129aZrcfs8h_uX7FODfrIVWt0_ulCNgaZ-nx8zUT5J7Jzr5I |
| linkProvider | Directory of Open Access Journals |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=%E8%9E%8D%E5%90%88%E6%B7%B1%E5%BA%A6%E8%AF%AF%E5%B7%AE%E5%8F%8D%E9%A6%88%E5%AD%A6%E4%B9%A0%E5%92%8C%E6%B3%A8%E6%84%8F%E5%8A%9B%E6%9C%BA%E5%88%B6%E7%9A%84%E7%9F%AD%E6%9C%9F%E9%A3%8E%E7%94%B5%E5%8A%9F%E7%8E%87%E9%A2%84%E6%B5%8B&rft.jtitle=%E7%94%B5%E5%8A%9B%E7%B3%BB%E7%BB%9F%E4%BF%9D%E6%8A%A4%E4%B8%8E%E6%8E%A7%E5%88%B6&rft.au=%E8%83%A1%E5%AE%87%E6%99%97&rft.au=%E6%9C%B1%E5%88%A9%E9%B9%8F&rft.au=%E6%9D%8E%E4%BD%B3%E5%8B%87&rft.au=%E6%9D%8E%E6%9D%A8&rft.date=2024-02-16&rft.pub=%E6%B9%96%E5%8D%97%E5%A4%A7%E5%AD%A6%E7%94%B5%E6%B0%94%E4%B8%8E%E4%BF%A1%E6%81%AF%E5%B7%A5%E7%A8%8B%E5%AD%A6%E9%99%A2%2C%E6%B9%96%E5%8D%97+%E9%95%BF%E6%B2%99+410082&rft.issn=1674-3415&rft.volume=52&rft.issue=4&rft.spage=100&rft.epage=108&rft_id=info:doi/10.19783%2Fj.cnki.pspc.230914&rft.externalDocID=jdq202404010 |
| thumbnail_s | http://utb.summon.serialssolutions.com/2.0.0/image/custom?url=http%3A%2F%2Fwww.wanfangdata.com.cn%2Fimages%2FPeriodicalImages%2Fjdq%2Fjdq.jpg |