A hybrid wind power forecasting model based on data mining and wavelets analysis

被引:113
作者
Azimi, R. [1 ]
Ghofrani, M. [2 ]
Ghayekhloo, M. [1 ]
机构
[1] Islamic Azad Univ, Qazvin Branch, Young Researchers & Elite Club, Qazvin, Iran
[2] Univ Washington, Sch Sci Technol Engn & Math STEM, Bothell, WA USA
关键词
Data mining; Data preprocessing; Forecasting; HANTS; Wavelet decomposition; Wind power; SPEED; ALGORITHMS;
D O I
10.1016/j.enconman.2016.09.002
中图分类号
O414.1 [热力学];
学科分类号
070201 [理论物理];
摘要
Accurate forecasting of wind power plays a key role in energy balancing and wind power integration into the grid. This paper proposes a novel time-series based K-means clustering method, named T.S.B. K-means, and a cluster selection algorithm to better extract features of wind time-series data. A hybrid of T.S.B K-means, discrete wavelet transform (DWT) and harnionic analysis time series (HANTS) methods, and a multilayer perceptron neural network (MLPNN) is developed for wind power forecasting. The proposed T.S.B K-means classifies data into separate groups and leads to more appropriate learning for neural networks by identifying anomalies and irregular patterns. This improves the accuracy of the forecast results. A cluster selection method is developed to determine the cluster that provides the best training for the MLPNN. This significantly accelerates the forecast process as the most appropriate portion of the data rather than the whole data is used for the NN training. The wind power data is decomposed by the Daubechies D4 wavelet transform, filtered by the HANTS, and pre-processed to provide the most. appropriate inputs for the MLPNN. Time-series analysis is used to pre-process the historical wind-power generation data and structure it into input-output series. Wind power datasets with diverse characteristics, from different wind farms located in the United States, are used to evaluate the accuracy of the hybrid forecasting method through various performance measures and different experiments. A comparative analysis with well-established forecasting models shows the superior performance of the proposed forecasting method. Published by Elsevier Ltd.
引用
收藏
页码:208 / 225
页数:18
相关论文
共 36 条
[1]
Almeida V, 2014, LECT NOTES ARTIF INT, V8779, P162, DOI 10.1007/978-3-319-11298-5_17
[2]
Very Short-Term Wind Speed Forecasting Using Spatio-Temporal Lazy Learning [J].
Appice, Annalisa ;
Pravilovic, Sonja ;
Lanza, Antonietta ;
Malerba, Donato .
DISCOVERY SCIENCE, DS 2015, 2015, 9356 :9-16
[3]
Arthur D, 2007, PROCEEDINGS OF THE EIGHTEENTH ANNUAL ACM-SIAM SYMPOSIUM ON DISCRETE ALGORITHMS, P1027
[4]
Long-term wind speed and power forecasting using local recurrent neural network models [J].
Barbounis, TG ;
Theocharis, JB ;
Alexiadis, MC ;
Dokopoulos, PS .
IEEE TRANSACTIONS ON ENERGY CONVERSION, 2006, 21 (01) :273-284
[5]
AWNN-Assisted Wind Power Forecasting Using Feed-Forward Neural Network [J].
Bhaskar, Kanna ;
Singh, S. N. .
IEEE TRANSACTIONS ON SUSTAINABLE ENERGY, 2012, 3 (02) :306-315
[6]
ENTROPY-BASED ALGORITHMS FOR BEST BASIS SELECTION [J].
COIFMAN, RR ;
WICKERHAUSER, MV .
IEEE TRANSACTIONS ON INFORMATION THEORY, 1992, 38 (02) :713-718
[7]
Dogan Yunus, 2013, Machine Learning and Data Mining in Pattern Recognition. 9th International Conference, MLDM 2013. Proceedings: LNCS 7988, P246, DOI 10.1007/978-3-642-39712-7_19
[8]
Intelligent optimized wind resource assessment and wind turbines selection in Huitengxile of Inner Mongolia, China [J].
Dong, Yao ;
Wang, Jianzhou ;
Jiang, He ;
Shi, Xiaomeng .
APPLIED ENERGY, 2013, 109 :239-253
[9]
Dunn J. C., 1973, Journal of Cybernetics, V3, P32, DOI 10.1080/01969727308546046
[10]
Forecasting the Wind Generation Using a Two-Stage Network Based on Meteorological Information [J].
Fan, Shu ;
Liao, James R. ;
Yokoyama, Ryuichi ;
Chen, Luonan ;
Lee, Wei-Jen .
IEEE TRANSACTIONS ON ENERGY CONVERSION, 2009, 24 (02) :474-482