A Novel Hybrid Approach Based on Wavelet Transform and Fuzzy ARTMAP Networks for Predicting Wind Farm Power Production

Author

Haque, Ashraf U. ; Mandal, P. ; Julian Meng ; SRIVASTAVA, ANURAG K. ; Tzu-Liang Tseng ; Senjyu, Tomonobu

Author_Institution

Dept. of Electr. & Comput. Eng., Montana State Univ., Bozeman, MT, USA

Volume

49

Issue

5

fYear

2013

fDate

Sept.-Oct. 2013

Firstpage

2253

Lastpage

2261

Abstract

This paper presents a novel hybrid intelligent algorithm based on the wavelet transform (WT) and fuzzy ARTMAP (FA) network for forecasting the power output of a wind farm utilizing meteorological information such as wind speed, wind direction, and temperature. The prediction capability of the proposed hybrid WT +FA model is demonstrated by an extensive comparison with a benchmark persistence method, other soft computing models, and hybrid models as well. The test results show a significant improvement in forecasting error through the application of a proposed hybrid WT +FA model. The proposed hybrid wind power forecasting strategy is applied to real-life data from Kent Hill wind farm located in New Brunswick, Canada.

Keywords

fuzzy neural nets; hybrid power systems; load forecasting; power engineering computing; wavelet transforms; wind power plants; Canada; FA network; Kent Hill wind farm; New Brunswick; WT network; benchmark persistence method; forecasting error; fuzzy ARTMAP network; hybrid WT+FA model; hybrid intelligent algorithm; hybrid model; hybrid wind power forecasting strategy; meteorological information; power output forecasting; real-life data; soft computing model; temperature; wavelet transform network; wind direction; wind farm power production prediction; wind speed; Fuzzy ARTMAP (FA); soft computing models (SCMs); wavelet transform (WT); wind farm power forecast;

fLanguage

English

Journal_Title

Industry Applications, IEEE Transactions on

Publisher

ieee

ISSN

0093-9994

Type

jour

DOI

10.1109/TIA.2013.2262452

Filename

6515351