摘要
以确定性短期风能预测为出发点,综述常用的4种统计模型的研究进展,包括时间序列方法、人工神经网络、支持向量机和深度学习。针对基础统计模型预测效果不佳的问题,提出各类混合模型。数据预处理、优化算法与基础统计模型之间的组合,或人工神经网络与卷积神经网络、循环神经网络等深度学习模型之间的组合,对预测水平都有很好的提升作用。
Considering the low prediction performances achieved by statistical models,various hybrid models have been proposed. By combining data preprocessing and optimization algorithms with basic statistical models or integrating artificial neural networks,convolutional neural networks,and recurrent neural networks,researchers can significantly improve the performance of short-term forecasting of wind energy.
作者
赵泽妮
云斯宁
贾凌云
史加荣
贺宁
杨柳
Zhao Zeni;Yun Sining;Jia Lingyun;Shi Jiarong;He Ning;Yang Liu(School of Materials Science and Engineering,Xi'an University of Architecture and Technology,Xi'an 710055,China;School of Science,Xi'an University of Architecture and Technology,Xi'an 710055,China;School of Mechanical and Electrical Engineering,Xi'an University of Architecture and Technology,Xi'an 710055,China;School of Architecture,Xi'an University of Architecture and Technology,Xi'an 710055,China)
出处
《太阳能学报》
EI
CAS
CSCD
北大核心
2022年第11期224-234,共11页
Acta Energiae Solaris Sinica
基金
国家重点研发计划(2018YFB1502902)。
关键词
风力发电
机器学习
预测
数据处理
混合系统
wind power
machine learning
forecasting
data processing
hybrid systems
