• 首页
  • 期刊简介
  • 编委会
  • 投稿指南
  • 收录情况
  • 杂志订阅
  • 联系我们
引用本文:陆冰鉴,周 鹏,王 兴,周 可.基于EEMD和LSTM的短期风速预测模型研究[J].软件工程,2020,23(3):43-48.【点击复制】
【打印本页】   【下载PDF全文】   【查看/发表评论】  【下载PDF阅读器】  
←前一篇|后一篇→ 过刊浏览
分享到: 微信 更多
基于EEMD和LSTM的短期风速预测模型研究
陆冰鉴,周 鹏,王 兴,周 可1,2
1.(1.南京信大气象科学技术研究院有限公司,江苏 南京 210044;2.
2.南京信息工程大学大气科学与环境气象国家级实验教学示范中心,江苏 南京 210044)
摘 要: 由于风具有较强的阵性和局地性,影响因子较多,利用机器学习相关技术进行风速的预测,往往会受这 些影响,降低预测的准确率,特别是对于瞬时大风的预测,准确度普遍不高。针对上述问题,提出一种基于集合经验模 态分解法(EEMD)和长短期记忆神经网络(LSTM)相结合的短期风速预测模型,该模型采用EEMD将风速序列分解为多个 频域相对稳定的子序列,进而改善经验模态分解法(EMD)模态混叠现象,再采用LSTM构建预测模型,实现短期风速预 测。该方法与其他预测方法相比,预测的精度更高,误差更小,验证了本文预测方法的可行性和有效性。
关键词: 风速预测;集合经验模态分解;经验模态分解;长短期记忆神经网络
中图分类号: TP183    文献标识码: A
基金项目: 江苏海事局科技项目(NIMST-XS-2019007);国家自然科学基金项目(41805033);中国气象局软科学研究项目(2019ZZXM45).
Research on Short-term Wind Speed Forecasting Model Based on EEMD and LSTM
LU Bingjian,ZHOU Peng,WANG Xing,ZHOU Ke1,2
1.( 1.Nanjing Xinda Institute of Meteorological Science and Technology Co., Ltd., Nanjing 210044, China;2.
2.National Demonstration Center for Experimental Atmospheric Science and Environmental Meteorology Education, Nanjing University of Information Science & Technology, Nanjing 210044, China)
Abstract: Because the wind has strong transient and regional characteristics,the impact factors are numerous.Using machine learning technology to predict wind speed will often be affected by these factors,reducing the accuracy of prediction. Especially for the prediction of instantaneous high winds,the accuracy is generally not high.In order to solve this problem,this paper proposes a short-term wind speed forecasting model based on EEMD and LSTM.The model uses the ensemble empirical mode decomposition (EEMD) method to decompose the wind speed sequence into multiple sub-sequences whose frequency domain is stable.This method improves the aliasing phenomenon of the empirical mode decomposition (EMD) method.Then,this paper uses the long short-term memory (LSTM) neural network to build the forecasting model to forecast short-term wind speed.Compared with other forecasting methods,this method has higher accuracy and less error,which verifies the feasibility and validity of this method.
Keywords: wind speed forecast;ensemble empirical mode decomposition;long short-term memory neural network


版权所有:软件工程杂志社
地址:辽宁省沈阳市浑南区新秀街2号 邮政编码:110179
电话:0411-84767887 传真:0411-84835089 Email:semagazine@neusoft.edu.cn
备案号:辽ICP备17007376号-1
技术支持:北京勤云科技发展有限公司

用微信扫一扫

用微信扫一扫