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
  • [21] Missing interpolation model for wind power data based on the improved CEEMDAN method and generative adversarial interpolation network
    Zhao, Lingyun
    Wang, Zhuoyu
    Chen, Tingxi
    Lv, Shuang
    Yuan, Chuan
    Shen, Xiaodong
    Liu, Youbo
    GLOBAL ENERGY INTERCONNECTION-CHINA, 2023, 6 (05): : 517 - 529
  • [22] Reconstruction of missing data in social network Based on Affinity Propagation
    Liu, Rongxin
    Liu, Qun
    PROCEEDINGS OF THE 4TH INTERNATIONAL CONFERENCE ON MECHATRONICS, MATERIALS, CHEMISTRY AND COMPUTER ENGINEERING 2015 (ICMMCCE 2015), 2015, 39 : 2483 - 2486
  • [23] Missing interpolation model for wind power data based on the improved CEEMDAN method and generative adversarial interpolation network
    Lingyun Zhao
    Zhuoyu Wang
    Tingxi Chen
    Shuang Lv
    Chuan Yuan
    Xiaodong Shen
    Youbo Liu
    Global Energy Interconnection, 2023, 6 (05) : 517 - 529
  • [24] An Improved Wavelet Neural Network Method for Wind Speed Forecasting
    Yao, Chuanan
    Yu, Yongchang
    JOURNAL OF COMPUTATIONAL AND THEORETICAL NANOSCIENCE, 2013, 10 (12) : 2860 - 2865
  • [25] Wind Speed Forecasting with Missing Values
    Akcay, Huseyin
    Filik, Tansu
    2017 SEVENTH INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND TECHNOLOGY (ICIST2017), 2017, : 51 - 56
  • [26] Ensemble interpolation of missing wind turbine nacelle wind speed data in wind farms based on robust particle swarm optimized generalized regression neural network
    Du, Jie
    Sun, Hongchuan
    Cao, Yijia
    Liu, Yubao
    Pan, Linlin
    Liu, Yuewei
    INTERNATIONAL JOURNAL OF GREEN ENERGY, 2019, 16 (14) : 1210 - 1219
  • [27] Short-Term Wind Speed Forecasting Based on Data Preprocessing and Improved Hybrid Prediction Network
    Chen, Gonggui
    Li, Lijun
    Qin, Feng
    2020 CHINESE AUTOMATION CONGRESS (CAC 2020), 2020, : 734 - 738
  • [28] Filling Missing Data in Target-Point Wind Speed Time Series
    Kolokythas, K.
    Argiriou, A. A.
    PERSPECTIVES ON ATMOSPHERIC SCIENCES, 2017, : 449 - 454
  • [29] Tuning data preprocessing techniques for improved wind speed prediction
    Ahmad, Ahmad
    Xiao, Xun
    Mo, Huadong
    Dong, Daoyi
    ENERGY REPORTS, 2024, 11 : 287 - 303
  • [30] Multiscale Encoder-Decoder Network for DAS Data Simultaneous Denoising and Reconstruction
    Zhong, Tie
    Cong, Zheng
    Wang, Hongzhou
    Lu, Shaoping
    Dong, Xintong
    Dong, Shiqi
    Cheng, Ming
    IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 2023, 61 : 1 - 15