Hourly Day-Ahead Wind Power Prediction Using the Hybrid Model of Variational Model Decomposition and Long Short-Term Memory

被引:70
作者
Shi, Xiaoyu [1 ]
Lei, Xuewen [1 ]
Huang, Qiang [1 ]
Huang, Shengzhi [1 ]
Ren, Kun [2 ]
Hu, Yuanyuan [3 ]
机构
[1] Xian Univ Technol, State Key Lab Ecohydraul Northwest Arid Reg, Xian 710048, Shaanxi, Peoples R China
[2] North China Univ Water Recourses & Elect Power, Inst Elect Power, Zhengzhou 450000, Henan, Peoples R China
[3] Yanan Univ, Sch Foreign Languages, Yanan 716000, Peoples R China
基金
中国国家自然科学基金;
关键词
wind power prediction; long short term memory; variational model decomposition (VMD); direct model; recursive model; SPEED; MULTISTEP; NETWORK;
D O I
10.3390/en11113227
中图分类号
TE [石油、天然气工业]; TK [能源与动力工程];
学科分类号
0807 ; 0820 ;
摘要
A more accurate hourly prediction of day-ahead wind power can effectively reduce the uncertainty of wind power integration and improve the competitiveness of wind power in power auction markets. However, due to the inherent stochastic and intermittent nature of wind energy, it is very difficult to sharply improve the multi-step wind power forecasting (WPF) accuracy. According to theory of direct and recursive multi-step prediction, this study firstly proposes the models of R (recursive)-VMD (variational model decomposition)-LSTM (long short-term memory) and D (direct)-VMD-LSTM for the hourly forecast of day-ahead wind power by using a combination of a novel and in-depth neural network forecasting model called LSTM and the variational model decomposition (VMD) technique. The data from these model tests were obtained from two real-world wind power series from a wind farm located in Henan, China. The experimental results show that LSTM can achieve more precise predictions than traditional neural networks, and that VMD has a good self-adaptive ability to remove the stochastic volatility and retain more adequate data information than empirical mode decomposition (EMD). Secondly, the R-VMD-LSTM and D-VMD-LSTM are comparatively studied to analyze the accuracy of each step. The results verify the effectiveness of the combination of the two models: The R-VMD-LSTM model provides a more accurate prediction at the beginning of a day, while the D-VMD-LSTM model provides a more accurate prediction at the end of a day.
引用
收藏
页数:20
相关论文
共 29 条
[2]   Multi-step Ahead Wind Forecasting Using Nonlinear Autoregressive Neural Networks [J].
Ahmed, Adil ;
Khalid, Muhammad .
SUSTAINABILITY IN ENERGY AND BUILDINGS 2017, 2017, 134 :192-204
[3]  
[Anonymous], P 2016 IEEE PES AS P
[4]  
Aydin O, 2017, 2017 4TH INTERNATIONAL CONFERENCE ON ELECTRICAL AND ELECTRONIC ENGINEERING (ICEEE 2017), P281, DOI 10.1109/ICEEE2.2017.7935834
[5]   Stochastic hydro-thermal scheduling optimization: An overview [J].
de Queiroz, Anderson Rodrigo .
RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2016, 62 :382-395
[6]   Examining the applicability of different sampling techniques in the development of decomposition-based streamflow forecasting models [J].
Fang, Wei ;
Huang, Shengzhi ;
Ren, Kun ;
Huang, Qiang ;
Huang, Guohe ;
Cheng, Guanhui ;
Li, Kailong .
JOURNAL OF HYDROLOGY, 2019, 568 :534-550
[7]   Copulas-based risk analysis for inter-seasonal combinations of wet and dry conditions under a changing climate [J].
Fang, Wei ;
Huang, Shengzhi ;
Huang, Guohe ;
Huang, Qiang ;
Wang, Hao ;
Wang, Lu ;
Zhang, Ying ;
Li, Pei ;
Ma, Lan .
INTERNATIONAL JOURNAL OF CLIMATOLOGY, 2019, 39 (04) :2005-2021
[8]   A review on the recent history of wind power ramp forecasting [J].
Gallego-Castillo, Cristobal ;
Cuerva-Tejero, Alvaro ;
Lopez-Garcia, Oscar .
RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2015, 52 :1148-1157
[9]  
Gensler A, 2016, IEEE SYS MAN CYBERN, P2858, DOI 10.1109/SMC.2016.7844673
[10]   Multi-step forecasting for wind speed using a modified EMD-based artificial neural network model [J].
Guo, Zhenhai ;
Zhao, Weigang ;
Lu, Haiyan ;
Wang, Jianzhou .
RENEWABLE ENERGY, 2012, 37 (01) :241-249