Open AccessGaussian mixture model‐based neural network for short‐term wind power forecast
Author(s) -
Chang Gary W.,
Lu HengJiu,
Wang PingKui,
Chang YungRuei,
Lee YeeDer
Publication year - 2017
Publication title -
international transactions on electrical energy systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.428
H-Index - 42
ISSN - 2050-7038
DOI - 10.1002/etep.2320
Subject(s) - wind power , artificial neural network , autoregressive model , term (time) , wind speed , wind power forecasting , gaussian , power (physics) , computer science , electric power system , meteorology , engineering , econometrics , mathematics , artificial intelligence , geography , electrical engineering , physics , quantum mechanics
Summary The wind power forecast has attracted much attention in recent years because of the significantly increasing number of large‐scale integrations of the wind power plants in the electric grid. In this paper, a Gaussian mixture model‐based neural network model is proposed to forecast the short‐term wind power generation. Actual measured wind power output data are adopted to train the proposed model. Test results of wind power obtained by autoregressive integrated moving average, radial basis function neural network, support vector regression, and the proposed method are then under comparisons. It shows that the proposed method can provide more accurate forecast of short‐term wind power output than other compared methods.