基于CEEMDAN-GWO-LSSVM的高铁沿线短期风速预测模型  

Short-term wind speed prediction model along high-speed railway based on CEEMDAN-GWO-LSSVM

作　　者：任俞霏 李磊[1,2] 过加锦[1,3] REN Yufei;LI Lei;GUO Jiajin(Key Laboratory of Urban Rail Transit Intelligent Operation and Maintenance Technology and Equipment of Zhejiang Province,Zhejiang Normal University,Jinhua 321004,China;College of Engineering,Zhejiang Normal University,Jinhua 321004,China;College of Mathematics and Computers Science,Zhejiang Normal University,Jinhua 321004,China)

机构地区：[1]浙江师范大学,浙江省城市轨道交通智能运维技术与装备重点实验室,浙江金华321004 [2]浙江师范大学工学院,浙江金华321004 [3]浙江师范大学数学与计算机科学学院,浙江金华321004

出　　处：《交通科技与经济》2023年第2期68-73,共6页Technology & Economy in Areas of Communications

基　　金：综合交通大数据应用技术国家工程实验室开放项目(DZYF20-06);金华市公益性技术应用研究项目(2022-4-040)。

摘　　要：为提升高铁沿线风速短期预测的精度,利用基于自适应去噪完全集合经验模态分解(CEEMDAN)和灰狼优化(GWO)与最小二乘支持向量机(LSSVM)模型对高铁沿线风速进行短期预测。以某高铁沿线每间隔1 min采样的风速数据作为仿真对象展开建模实验并与其他组合预测模型进行比对。结果表明:CEEMDAN-GWO-LSSVM模型可以显著提升风速预测精度和准确性,其中均方误差(MSE)、平均绝对误差(MAE)和均方根误差(RMSE)3项评价指标提升程度分别达71.17%、46.14%和42.49%,均为最高。降低预测过程中产生的误差,为我国高速铁路沿线的短期风速预测研究提供有益借鉴。In order to improve the accuracy of short-term wind speed prediction along the high-speed railway,a model based on Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN),Gray Wolf Optimization(GWO)and Least Squares Support Vector Machine(LSSVM)was used to predict the wind speed along the high-speed railway.The wind speed data sampled every 1 min along a high-speed railway was used as the simulation object to conduct the modeling experiment and compare with other combined prediction models.The results show that the CEEMDAN-GWO-LSSVM model can significantly improve the accuracy of wind speed prediction,and the improvement degree of Mean Square Error(MSE),Mean Absolute Error(MAE)and Root Mean Square Error(RMSE)are 71.17%,46.14%and 42.49%,respectively,which are the highest.Reducing the error in the prediction process will provide useful reference for the research of short-term wind speed prediction along the high-speed railway in China.

关 键 词：高速铁路 风速短期预测 自适应去噪完全集合经验模态分解 灰狼优化算法 最小二乘支持向量机 

分 类 号：U298.1[交通运输工程—交通运输规划与管理]