Advanced Deep Learning Approach for Probabilistic Wind Speed Forecasting

被引:72
作者
Afrasiabi, Mousa [1 ]
Mohammadi, Mohammad [1 ]
Rastegar, Mohammad [1 ]
Afrasiabi, Shahabodin [1 ]
机构
[1] Shiraz Univ, Sch Elect & Comp Engn, Shiraz 7194684636, Iran
关键词
Forecasting; Wind speed; Time series analysis; Logic gates; Feature extraction; Probability density function; Autoregressive processes; Deep mixture network; probability density function (PDF); spatial-temporal features; wind speed forecasting; NEURAL-NETWORK; POWER; REGRESSION; ENSEMBLE;
D O I
10.1109/TII.2020.3004436
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
One of the critical challenges in wind energy development is the uncertainty quantification. Prior knowledge about the wind speed in look-ahead times in shape of probabilistic information plays a pivotal role in the optimal operation and planning in the electrical networks. In this article, we design a deep learning-based approach to characterize the probability density function (PDF) of the wind for the next hours. The proposed method is directly applicable to raw data and directly constructs PDFs and enhances the level of accuracy and reliability as well as computational efficiency. Furthermore, we utilize the convolutional neural network to enhance learning spatial features. To provide a better understanding of temporal features, a recurrent neural network, called gated recurrent unit, is utilized. To directly construct PDFs, a gradient-based loss function is proposed, and the training procedure is modified. The effectiveness and superiority of the proposed probabilistic wind speed forecasting are verified by two actual datasets, i.e., London, England, and Shiraz, Iran, and comprehensive numerical results validate the performance of the proposed approach in comparison with several state-of-the-art and previously investigated approaches in terms of sharpness, accuracy, and reliability.
引用
收藏
页码:720 / 727
页数:8
相关论文
共 34 条
[1]   Multi-agent microgrid energy management based on deep learning forecaster [J].
Afrasiabi, Mousa ;
Mohammadi, Mohammad ;
Rastegar, Mohammad ;
Kargarian, Amin .
ENERGY, 2019, 186
[2]   Probabilistic deep neural network price forecasting based on residential load and wind speed predictions [J].
Afrasiabi, Mousa ;
Mohammadi, Mohammad ;
Rastegar, Mohammad ;
Kargarian, Amin .
IET RENEWABLE POWER GENERATION, 2019, 13 (11) :1840-1848
[3]   Power transformers internal fault diagnosis based on deep convolutional neural networks [J].
Afrasiabi, Mousa ;
Afrasiabi, Shahabodin ;
Parang, Benyamin ;
Mohammadi, Mohammad .
JOURNAL OF INTELLIGENT & FUZZY SYSTEMS, 2019, 37 (01) :1165-1179
[4]   Integration of Accelerated Deep Neural Network Into Power Transformer Differential Protection [J].
Afrasiabi, Shahabodin ;
Afrasiabi, Mousa ;
Parang, Benyamin ;
Mohammadi, Mohammad .
IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS, 2020, 16 (02) :865-876
[5]   Designing a composite deep learning based differential protection scheme of power transformers [J].
Afrasiabi, Shahabodin ;
Afrasiabi, Mousa ;
Parang, Benyamin ;
Mohammadi, Mohammad .
APPLIED SOFT COMPUTING, 2020, 87
[6]  
Afrasiabi S, 2019, 2019 10TH INTERNATIONAL POWER ELECTRONICS, DRIVE SYSTEMS AND TECHNOLOGIES CONFERENCE (PEDSTC), P155, DOI [10.1109/PEDSTC.2019.8697244, 10.1109/pedstc.2019.8697244]
[7]   Wavelet-Based Decompositions in Probabilistic Load Forecasting [J].
Alfieri, Luisa ;
De Falco, Pasquale .
IEEE TRANSACTIONS ON SMART GRID, 2020, 11 (02) :1367-1376
[8]  
[Anonymous], 2014, RENEWABLE ENERGY IRA
[9]  
[Anonymous], 2019, EUR TRANSP
[10]  
[Anonymous], 2013, LONDON DATASTORE