Missing wind speed data reconstruction with improved context encoder network

被引:11
|
作者
Jing, Bo [1 ]
Pei, Yan [1 ]
Qian, Zheng [1 ]
Wang, Anqi [1 ]
Zhu, Siyu [1 ]
An, Jiayi [1 ]
机构
[1] Beihang Univ, Xueyuan Rd 37, Beijing 100191, Peoples R China
关键词
Wind energy; Data reconstruction; Missing wind speed data; Context encoders; IMPUTATION;
D O I
10.1016/j.egyr.2022.02.177
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
Missing wind speed data are mainly caused by harsh weather, wind turbine failures, and data transmission errors, which have adverse effects on the performance of wind power forecasting, power curve modeling, and energy assessment. Inspired by context encoders (CE), this paper proposes an improved context encoder network (ICE) for missing wind speed data reconstruction. An auto-encoder architecture with multiple one-dimensional convolutional layers is established for data generation. During network training, a joint loss function that includes reconstruction loss and adversarial loss is presented to obtain the stable and near-real reconstructed wind speed data. We add an Inception layer to the generator network to automatically select the appropriate convolutional filters and then recalibrate the channel relationship between feature maps via the squeeze-and-excitation network. At last, this paper uses wind speed data collected from an on-shore wind farm to verify the effectiveness of the proposed network. The results show that the mean absolute error (MAE) and root mean square error (RMSE) of the ICE network in different data missing rates are 0.019-0.021 and 0.021-0.025, respectively. It has the lowest reconstruction errors compared with six typical data reconstruction methods. (c) 2022 The Authors. Published by Elsevier Ltd.& nbsp;
引用
收藏
页码:3386 / 3394
页数:9
相关论文
共 50 条
  • [31] Missing data recovery of wind speed in wind farms: A spatial-temporal tensor decomposition approach
    Tan, Hang
    Lin, Shengmao
    Xu, Xuefang
    Shi, Peiming
    Li, Ruixiong
    Wang, Shuying
    JOURNAL OF RENEWABLE AND SUSTAINABLE ENERGY, 2023, 15 (03)
  • [32] A method of handling missing data in the context of learning Bayesian network structure
    Chen, Chong
    Yu, Hua
    Wang, Juyun
    APPLIED SCIENCE AND PRECISION ENGINEERING INNOVATION, PTS 1 AND 2, 2014, 479-480 : 906 - +
  • [33] Data Completing of Missing Wind Power Data Based on Adaptive BP Neural Network
    Yang Mao
    Ma Jian
    2016 INTERNATIONAL CONFERENCE ON PROBABILISTIC METHODS APPLIED TO POWER SYSTEMS (PMAPS), 2016,
  • [34] Wind Speed Forecast for Wind Farms Based on Phase Space Reconstruction of Wavelet Neural Network
    Xu, Xiaobing
    He, Jun
    Wang, Jianping
    MATERIALS SCIENCE AND INFORMATION TECHNOLOGY, PTS 1-8, 2012, 433-440 : 840 - 845
  • [35] Improved deep mixed kernel randomized network for wind speed prediction
    Rayi, Vijaya Krishna
    Bisoi, Ranjeeta
    Mishra, S. P.
    Dash, P. K.
    CLEAN ENERGY, 2023, 7 (05): : 1006 - 1031
  • [36] Data-driven reconstruction of wind speed randomness in an urban area
    Walle-Garcia, Otoniel
    Soto-Rocha, M. Valentina I.
    Saldana-Jimenez, Fernando
    Hernandez-Cabrera, Francisco
    Almaguer-Martinez, Francisco-Javier
    STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT, 2025, : 1237 - 1252
  • [37] Improved Wind Speed Prediction Results by Artificial Neural Network Method
    Sirdas, Asilhan Sevinc
    Nilcan, Akatas
    Ercan, Izgi
    EXERGY FOR A BETTER ENVIRONMENT AND IMPROVED SUSTAINABILITY 2: APPLICATIONS, 2018, : 651 - 665
  • [38] Missing data in the forensic context
    Kadane, JB
    Terrin, N
    JOURNAL OF THE ROYAL STATISTICAL SOCIETY SERIES A-STATISTICS IN SOCIETY, 1997, 160 : 351 - 357
  • [39] Improved tolerance to missing data in myocardial perfusion SPET using OSEM reconstruction
    Hatton, RL
    Hutton, BF
    Angelides, S
    Choong, KKL
    Larcos, G
    EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING, 2004, 31 (06) : 857 - 861
  • [40] Improved tolerance to missing data in myocardial perfusion SPET using OSEM reconstruction
    R. L. Hatton
    B. F. Hutton
    S. Angelides
    K. K. L. Choong
    G. Larcos
    European Journal of Nuclear Medicine and Molecular Imaging, 2004, 31 : 857 - 861