ScholarMate
English简体中文繁體中文
客服热线:400-1616-289
登录注册
期刊论文

Deep learning for renewable energy forecasting: A taxonomy, and systematic literature review

Ying, Changtian*; Wang, Weiqing; Yu, Jiong; Li, Qi; Yu, Donghua; Liu, Jianhua绍兴文理学院; 新疆大学
JOURNAL OF CLEANER PRODUCTION2023-1-15DOI: 10.1016/j.jclepro.2022.135414
47被引14阅读
引用收藏
分享

摘要

In order to identify power production and demand in realtime for efficient and dependable management for diverse renewable energy systems, precise and intuitive renewable energy predictions are required. Deep learning can be exploited to handle a variety of operations and maintenance improvement challenges, as well as develop better methods and perspectives for medium-and long-term energy prediction. This paper provides a detailed literature and bibliometric review of deep learning models for effective renewable energy forecasting. To begin, data was gathered via the Web of Science (WoS) library to access a large amount of articles and journals. In WoS, a total of 276 publications were extracted, including five different types, including Articles (261), Reviews (13), Early Access (10), Proceedings Paper (5), Editorial Material (2), and Data Paper (1). Then, literature statistics analyzed top 10 productive country, author, institution, journal. Overall keyword analysis are explored and discussed from various aspects like most frequency keywords, keywords analysis by year, keywords co-occurrence analysis, keywords co-occurrence graph, topic evolution-accumulation, topic evolution weighted. In addition, literature statistics of renewable energy are evaluated for wind energy, solar energy, ocean energy, hydrogen energy. Deep learning models can be leveraged to anticipate underneath a variety of uncertainty arising from renewable energy sources that are fluctuating. Furthermore, the estimated prediction accuracy requirements are given, and the keywords analysis of the deep learning forecasting models iare demonstrated from the perspectives of SAE (Stacked AutoEncoder), DBN(Deep Belief Network), CNN(Convolutional Neural Networks), GAN(Generative Adversarial Networks), and RNN(Recurrent Neural Network). Due to various shifting weather conditions as well as other variables, the forecasting model responds differently by various types of datasets. Deep learning methods offer intriguing potential discoveries in the field of energy forecasting. The relevant aspects and suggestions for future research were highlighted in the conclusion to conquer the projected barriers.

学科与关键词

关键词
Deep learningRenewable energy literature reviewbibliometric analysis forecasting
相关
加载中…

文献加载失败,请重试

重试

发表信息

论文状态
公开发表
期刊
JOURNAL OF CLEANER PRODUCTION
发表日期
2023-01-15
卷期
第 384 卷
页码
135414
DOI
10.1016/j.jclepro.2022.135414
语言
ENGLISH
成果收录
SCIE
资助标注
Special Project For Preliminary Research Of National Major Basic Research [SQ2021xjkk01800-2]; Sub Topics Of Major National Research And Development Projects [202008120002]; National Natural Science Foundation of China [61862060, 52067020]; Zhejiang Provincial Natural Science Foundation of China [LHQ20F020001, ZY21F020007]; Huadong Engineering Corporation limited [LHQ20F020001, ZY21F020007]; Scientific Research Project of Zhejiang Provincial Department of Education [Y201940952]; Teaching Reform Project of Shaoxing University; Scientific Research of Shengzhou Provincial high-tech Park Research Institute of Shaoxing University

作者

  • Y

    Ying, Changtian (通讯) (第一作者)

    xinjiang univ · shaoxing univ

  • W

    Wang, Weiqing

    xinjiang univ

查看全部 6 位作者收起作者
  • Y

    Yu, Jiong

    xinjiang univ

  • L

    Li, Qi

    shaoxing univ

  • Y

    Yu, Donghua

    shaoxing univ

  • L

    Liu, Jianhua

    shaoxing univ

登录解锁更多功能

  • 收藏这篇,随时在“我的 · 收藏”找回
  • 认领你的成果,生成推广素材
  • 关注作者获取最新成果
  • 加入项目组、协同写作
注册 / 登录

产品服务

  • 科研之友
  • 创新城
  • 科创云

服务支持

  • 帮助中心
  • 隐私政策
  • 服务条款

联系方式

在线客服:【】
客服热线:400-1616-289
电子邮箱:support@scholarmate.com

关注或下载科研之友

微信二维码
微信公众号
客户端下载二维码
下载客户端
科研成果科研人员科研机构科研动态爱瑞思软件

©2026 深圳市科研之友网络服务有限公司

公安备案图标粤公网安备 44030502000213
粤ICP备 16046710 号粤B2-20110417