Hour-ahead wind power and speed forecasting using simultaneous perturbation stochastic approximation (SPSA) algorithm and neural network with fuzzy inputs

被引：92
|
作者：
Hong, Ying-Yi [1 ]
Chang, Huei-Lin [1 ]
Chiu, Ching-Sheng [1 ]
机构：
[1] Chung Yuan Christian Univ, Dept Elect Engn, Chungli 320, Taiwan
来源：
ENERGY | 2010年 / 35卷 / 09期
关键词：
Forecasting; Fuzzy set; Neural network; Stochastic optimization; Wind power; GRADIENT APPROXIMATION; OPTIMIZATION; GENERATION; SYSTEMS; MODELS;
D O I：
10.1016/j.energy.2010.05.041
中图分类号：
O414.1 [热力学];
学科分类号：
摘要：
Wind energy is currently one of the types of renewable energy with a large generation capacity. However, since the operation of wind power generation is challenging due to its intermittent characteristics, forecasting wind power generation efficiently is essential for economic operation. This paper proposes a new method of wind power and speed forecasting using a multi-layer feed-forward neural network (MFNN) to develop forecasting in time-scales that can vary from a few minutes to an hour. Inputs for the MFNN are modeled by fuzzy numbers because the measurement facilities provide maximum, average and minimum values. Then simultaneous perturbation stochastic approximation (SPSA) algorithm is employed to train the MFNN. Real wind power generation and wind speed data measured at a wind farm are used for simulation. Comparative studies between the proposed method and traditional methods are shown. (C) 2010 Elsevier Ltd. All rights reserved.
引用
收藏
页码：3870 / 3876
页数：7
相关论文
共 38 条
  • [1] A Hour-Ahead Wind Speed Forecasting Using One-Dimensional Convolutional Neural Network
    Nazemi, Mohammadhossein
    Chowdhury, Shaikat
    Khan, Alimul Haque
    Liang, Xiaodong
    [J]. 2023 IEEE CANADIAN CONFERENCE ON ELECTRICAL AND COMPUTER ENGINEERING, CCECE, 2023,
  • [2] Hour-Ahead Wind Speed and Power Forecasting Using Empirical Mode Decomposition
    Hong, Ying-Yi
    Yu, Ti-Hsuan
    Liu, Ching-Yun
    [J]. ENERGIES, 2013, 6 (12): : 6137 - 6152
  • [3] Hour-Ahead Photovoltaic Power Forecasting Using an Analog Plus Neural Network Ensemble Method
    Wang, Jingyue
    Qian, Zheng
    Wang, Jingyi
    Pei, Yan
    [J]. ENERGIES, 2020, 13 (12)
  • [4] Simultaneous Perturbation Stochastic Approximation Algorithm Combined with Neural Network and Fuzzy Simulation
    宁玉富
    唐万生
    郭长友
    [J]. Transactions of Tianjin University, 2008, (01) : 43 - 49
  • [5] Simultaneous perturbation stochastic approximation algorithm combined with neural network and fuzzy simulation
    Ning Y.
    Tang W.
    Guo C.
    [J]. Transactions of Tianjin University, 2008, 14 (1) : 43 - 49
  • [6] One Hour-Ahead Wind Speed Forecasting of Sotavento Galicia SA Wind Farm by Using ANN
    Sahay, Kishan Bhushan
    Shukla, Prakeern
    [J]. 2018 6TH INTERNATIONAL ELECTRICAL ENGINEERING CONGRESS (IEECON), 2018,
  • [7] Hour-Ahead Solar Forecasting Program Using Back Propagation Artificial Neural Network
    Laopaiboon, Tanawat
    Ongsakul, Weerakorn
    Panyainkaew, Pradya
    Sasidharan, Nikhill
    [J]. PROCEEDINGS OF THE 2018 INTERNATIONAL CONFERENCE AND UTILITY EXHIBITION ON GREEN ENERGY FOR SUSTAINABLE DEVELOPMENT (ICUE 2018), 2018,
  • [8] Hour-Ahead Wind Power Prediction for Power Systems using Hidden Markov Models and Viterbi Algorithm
    Jafarzadeh, Saeed
    Fadali, Sami
    Evrenosoglu, Cansin Yaman
    Livani, Hanif
    [J]. IEEE POWER AND ENERGY SOCIETY GENERAL MEETING 2010, 2010,
  • [9] Hour-Ahead Power Generating Forecasting of Photovoltaic Plants Using Artificial Neural Networks Days Tuning
    Ouedraogo, Faouzi Brice
    Zhang, Xiao-Yan
    Chen, Chao-Rong
    Lee, Ching-Yin
    [J]. 2020 IEEE INTERNATIONAL CONFERENCE ON SYSTEMS, MAN, AND CYBERNETICS (SMC), 2020, : 3874 - 3879
  • [10] A Novel Two-Dimensional Convolutional Neural Network-Based an Hour-Ahead Wind Speed Prediction Method
    Nazemi, Mohammadhossein
    Chowdhury, Shaikat
    Liang, Xiaodong
    [J]. IEEE ACCESS, 2023, 11 : 118878 - 118889
1234