Learning Heterogeneous Features Jointly: A Deep End-to-End Framework for Multi-Step Short-Term Wind Power Prediction

被引:35
作者
Chen, Jinfu [1 ]
Zhu, Qiaomu [1 ]
Li, Hongyi [2 ]
Zhu, Lin [3 ]
Shi, Dongyuan [1 ]
Li, Yinhong [1 ]
Duan, Xianzhong [1 ]
Liu, Yilu [3 ,4 ]
机构
[1] Huazhong Univ Sci & Technol, Sch Elect & Elect Engn, State Key Lab Adv Electromagnet Engn & Technol, Wuhan 430074, Peoples R China
[2] State Grid Hunan Elect Power Co Ltd, Econ & Technol Res Inst, Changsha 410004, Peoples R China
[3] Univ Tennessee, Dept Elect Engn & Comp Sci, Knoxville, TN 37996 USA
[4] Oak Ridge Natl Lab, POB 2009, Oak Ridge, TN 37831 USA
关键词
Wind power generation; Feature extraction; Predictive models; Task analysis; Time measurement; Wind speed; Power measurement; Deep learning; heterogeneous features; multimodal learning; multitask learning; sequence-to-sequence prediction; wind power prediction; NEURAL-NETWORKS; SPEED; FORECASTS; MACHINE; INPUT; MODEL;
D O I
10.1109/TSTE.2019.2940590
中图分类号
X [环境科学、安全科学];
学科分类号
08 ; 0830 ;
摘要
Leveraging multiple heterogeneous measurements to predict wind power has long been a challenging task in the electrical community. In this paper, a deep architecture incorporated with multitask learning and multimodal learning for wind power prediction, termed predictive stacked autoencoder (PSAE), is presented. PSAE is a unified framework integrating multiple stacked autoencoders (SAEs), one feature fusion layer, and one prediction terminal layer, which expands the architecture from two spatial dimensions, including the depth and width, compared to conventional prediction models. Initially, the SAEs at the bottom of PSAE extracted features from multiple kinds of measurements respectively. Following, the feature fusion layer encodes the high-order features extracted by different SAEs into a unified feature that is more informative and representative for wind power prediction. Finally, the prediction terminal layer functions as a regression machine which generates the predicted targets based on the fusion features. Trained in an end-to-end (E2E) manner, PSAE is capable of learning heterogeneous features jointly and achieving the prediction task of sequence-to-sequence (S2S). Experiments for multi-step short-term predictions are conducted on real-world data, and the results demonstrate the superiority of PSAE to prior methods.
引用
收藏
页码:1761 / 1772
页数:12
相关论文
共 54 条
[1]  
Abadi M., 2016, ARIXIV160508695V2
[2]   Review of the use of Numerical Weather Prediction (NWP) Models for wind energy assessment [J].
Al-Yahyai, Sultan ;
Charabi, Yassine ;
Gastli, Adel .
RENEWABLE & SUSTAINABLE ENERGY REVIEWS, 2010, 14 (09) :3192-3198
[3]   Short-term prediction of wind power using EMD and chaotic theory [J].
An, Xueli ;
Jiang, Dongxiang ;
Zhao, Minghao ;
Liu, Chao .
COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION, 2012, 17 (02) :1036-1042
[4]  
[Anonymous], 2010, IEEE PES GEN M
[5]  
[Anonymous], 2011, STATE ART SHORT TERM
[6]  
[Anonymous], 2012, Probability and Statistics
[7]   A sequential simulation technique for adequacy evaluation of generating systems including wind energy [J].
Billinton, R ;
Chen, H ;
Ghajar, R .
IEEE TRANSACTIONS ON ENERGY CONVERSION, 1996, 11 (04) :728-734
[8]   Statistical analysis of wind power forecast error [J].
Bludszuweit, Hans ;
Antonio Dominguez-Navarro, Jose ;
Llombart, Andres .
IEEE TRANSACTIONS ON POWER SYSTEMS, 2008, 23 (03) :983-991
[9]   Wind Pattern Recognition and Reference Wind Mast Data Correlations With NWP for Improved Wind- Electric Power Forecasts [J].
Buhan, Serkan ;
Ozkazanc, Yakup ;
Cadirci, Isik .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2016, 12 (03) :991-1004
[10]   Multitask learning [J].
Caruana, R .
MACHINE LEARNING, 1997, 28 (01) :41-75