Short-term wind speed time series forecasting based on a hybrid method with multiple objective optimization for non-convex target | |
Dong, Yunxuan1; Wang, Jing2; Xiao, Ling3; Fu, Tonglin4,5,6 | |
2021-01-15 | |
发表期刊 | Energy |
ISSN | 03605442 |
卷号 | 215 |
摘要 | Accurate and reliable wind speed forecasting (WSF) is crucial for wind power systems. As one of the effective forecast methods, machine learning (ML) methods are employed for wind speed time series forecasting because the excellent ability in fitting the relationship between data and cost function. However, the cost functions with non-convexity make the whole problem poor interpretability and poor robustness. In this paper, a novel hybrid supervised approach is proposed to solve the above problems. The proposed approach has adopted local convolutional neural networks (LCNNs) for convexity preserving of the cost function, in this way, a non-convex problem can be transformed as a convex problem so that heuristic optimization algorithms is adopted to find optimal parameters, and it helps to construct a more stable model. Highway Gate (HG) algorithm is adopted to decrease the computation complexity of the proposed model. The numerical simulation results indicate that the proposed method is not only effective for solving convergence problem cost by non-convexity, but also beneficial to improve accuracy and stability of the traditional ML for wind speed time series forecasting. © 2020 Elsevier Ltd |
关键词 | Convergence of numerical methods Convolutional neural networks Cost functions Forecasting Heuristic algorithms Optimization Time series Wind powerComputation complexity Convergence problems Convexity-preserving Heuristic optimization algorithms Multiple-objective optimization Optimal parameter Wind speed forecasting Wind speed time series |
DOI | 10.1016/j.energy.2020.119180 |
收录类别 | EI ; SCIE |
语种 | 英语 |
WOS研究方向 | Thermodynamics ; Energy & Fuels |
WOS类目 | Thermodynamics ; Energy & Fuels |
WOS记录号 | WOS:000596834000005 |
出版者 | Elsevier Ltd |
EI入藏号 | 20204709513428 |
EI主题词 | Wind |
EI分类号 | 443.1 Atmospheric Properties - 615.8 Wind Power (Before 1993, use code 611 ) - 723.1 Computer Programming - 921.5 Optimization Techniques - 921.6 Numerical Methods - 922.2 Mathematical Statistics |
来源库 | Compendex |
分类代码 | 443.1 Atmospheric Properties - 615.8 Wind Power (Before 1993, use code 611 ) - 723.1 Computer Programming - 921.5 Optimization Techniques - 921.6 Numerical Methods - 922.2 Mathematical Statistics |
引用统计 | |
文献类型 | 期刊论文 |
条目标识符 | https://ir.lut.edu.cn/handle/2XXMBERH/132386 |
专题 | 法学院 |
通讯作者 | Xiao, Ling |
作者单位 | 1.Univ Macau, Dept Elect & Comp Engn, Macau, Peoples R China; 2.Lanzhou Univ Technol, Sch Law, Lanzhou 730050, Gansu, Peoples R China; 3.Chongqing Univ Posts & Telecommun, Sch Econ & Management, Chongqing 400065, Peoples R China; 4.LongDong Univ, Sch Math & Stat, Qingyang, Gansu, Peoples R China; 5.Chinese Acad Sci, Shapotou Desert Res & Expt Stn, Northwest Inst Ecoenvironm & Resources, Lanzhou 730000, Peoples R China; 6.Univ Chinese Acad Sci, Beijing 100049, Peoples R China |
推荐引用方式 GB/T 7714 | Dong, Yunxuan,Wang, Jing,Xiao, Ling,et al. Short-term wind speed time series forecasting based on a hybrid method with multiple objective optimization for non-convex target[J]. Energy,2021,215. |
APA | Dong, Yunxuan,Wang, Jing,Xiao, Ling,&Fu, Tonglin.(2021).Short-term wind speed time series forecasting based on a hybrid method with multiple objective optimization for non-convex target.Energy,215. |
MLA | Dong, Yunxuan,et al."Short-term wind speed time series forecasting based on a hybrid method with multiple objective optimization for non-convex target".Energy 215(2021). |
条目包含的文件 | 条目无相关文件。 |
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。
修改评论