一种新的基于深度学习的数字孪生模型,用于减轻风电场的尾流效应

IF 5.9 Q2 ENERGY & FUELS
Abdollah Kavousi-Fard , Morteza Dabbaghjamanesh , Morteza Sheikh , Tao Jin
{"title":"一种新的基于深度学习的数字孪生模型,用于减轻风电场的尾流效应","authors":"Abdollah Kavousi-Fard ,&nbsp;Morteza Dabbaghjamanesh ,&nbsp;Morteza Sheikh ,&nbsp;Tao Jin","doi":"10.1016/j.ref.2025.100686","DOIUrl":null,"url":null,"abstract":"<div><div>Wind energy plays a significant role in sustainable power generation in power systems such as energy hubs, microgrids, smart grids and smart cities. On the other hand, some challenges such as wake effects in wind farms can lead to reduced efficiency and increased maintenance costs for the wind farms. This paper presents a cutting-edge approach to tackle these challenges through the development of a novel deep learning-based digital twin model. The proposed model integrates advanced deep learning algorithms with digital twin technology to accurately simulate and predict wake effects within wind farms. By leveraging data from various sensors and weather forecasts, the model can dynamically adjust turbine settings and optimize energy production in real-time. Key features of the digital twin include a convolutional neural network (CNN) for spatial analysis of wake patterns, a recurrent neural network (RNN) for temporal modelling of wind behaviour, and a reinforcement learning (RL) framework for autonomous decision-making. Through extensive simulations and validation against field data, the model demonstrates superior performance in mitigating wake effects and improving overall wind farm efficiency. This research contributes to the advancement of renewable energy technologies by providing a robust and scalable solution for optimizing wind farm operations and maximizing energy output.</div></div>","PeriodicalId":29780,"journal":{"name":"Renewable Energy Focus","volume":"53 ","pages":"Article 100686"},"PeriodicalIF":5.9000,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A novel deep learning based digital twin model for mitigating wake effects in wind farms\",\"authors\":\"Abdollah Kavousi-Fard ,&nbsp;Morteza Dabbaghjamanesh ,&nbsp;Morteza Sheikh ,&nbsp;Tao Jin\",\"doi\":\"10.1016/j.ref.2025.100686\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Wind energy plays a significant role in sustainable power generation in power systems such as energy hubs, microgrids, smart grids and smart cities. On the other hand, some challenges such as wake effects in wind farms can lead to reduced efficiency and increased maintenance costs for the wind farms. This paper presents a cutting-edge approach to tackle these challenges through the development of a novel deep learning-based digital twin model. The proposed model integrates advanced deep learning algorithms with digital twin technology to accurately simulate and predict wake effects within wind farms. By leveraging data from various sensors and weather forecasts, the model can dynamically adjust turbine settings and optimize energy production in real-time. Key features of the digital twin include a convolutional neural network (CNN) for spatial analysis of wake patterns, a recurrent neural network (RNN) for temporal modelling of wind behaviour, and a reinforcement learning (RL) framework for autonomous decision-making. Through extensive simulations and validation against field data, the model demonstrates superior performance in mitigating wake effects and improving overall wind farm efficiency. This research contributes to the advancement of renewable energy technologies by providing a robust and scalable solution for optimizing wind farm operations and maximizing energy output.</div></div>\",\"PeriodicalId\":29780,\"journal\":{\"name\":\"Renewable Energy Focus\",\"volume\":\"53 \",\"pages\":\"Article 100686\"},\"PeriodicalIF\":5.9000,\"publicationDate\":\"2025-02-13\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Renewable Energy Focus\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S1755008425000080\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENERGY & FUELS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Renewable Energy Focus","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S1755008425000080","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENERGY & FUELS","Score":null,"Total":0}
引用次数: 0

摘要

风能在能源枢纽、微电网、智能电网和智慧城市等电力系统的可持续发电中发挥着重要作用。另一方面,一些挑战,如风电场的尾流效应,可能导致风电场的效率降低和维护成本增加。本文通过开发一种新的基于深度学习的数字孪生模型,提出了一种解决这些挑战的前沿方法。所提出的模型集成了先进的深度学习算法和数字孪生技术,以准确模拟和预测风电场内的尾流效应。通过利用来自各种传感器和天气预报的数据,该模型可以动态调整涡轮机设置并实时优化能源生产。数字孪生的主要特征包括用于尾流模式空间分析的卷积神经网络(CNN),用于风行为时间建模的循环神经网络(RNN),以及用于自主决策的强化学习(RL)框架。通过大量的模拟和现场数据验证,该模型在减轻尾流效应和提高整体风电场效率方面表现出卓越的性能。这项研究为优化风电场运营和最大化能源输出提供了一个强大的、可扩展的解决方案,有助于可再生能源技术的进步。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
A novel deep learning based digital twin model for mitigating wake effects in wind farms
Wind energy plays a significant role in sustainable power generation in power systems such as energy hubs, microgrids, smart grids and smart cities. On the other hand, some challenges such as wake effects in wind farms can lead to reduced efficiency and increased maintenance costs for the wind farms. This paper presents a cutting-edge approach to tackle these challenges through the development of a novel deep learning-based digital twin model. The proposed model integrates advanced deep learning algorithms with digital twin technology to accurately simulate and predict wake effects within wind farms. By leveraging data from various sensors and weather forecasts, the model can dynamically adjust turbine settings and optimize energy production in real-time. Key features of the digital twin include a convolutional neural network (CNN) for spatial analysis of wake patterns, a recurrent neural network (RNN) for temporal modelling of wind behaviour, and a reinforcement learning (RL) framework for autonomous decision-making. Through extensive simulations and validation against field data, the model demonstrates superior performance in mitigating wake effects and improving overall wind farm efficiency. This research contributes to the advancement of renewable energy technologies by providing a robust and scalable solution for optimizing wind farm operations and maximizing energy output.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Renewable Energy Focus
Renewable Energy Focus Renewable Energy, Sustainability and the Environment
CiteScore
7.10
自引率
8.30%
发文量
0
审稿时长
48 days
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信