Long-Term Wind Speed Forecasting and General Pattern Recognition Using Neural Networks

Long-term forecasting of wind speed has become a research hot spot in many different areas such as restructured electricity markets, energy management, and wind farm optimal design. However, wind energy with unstable and intermittent characteristics entails establishing accurate predicted data to avoid inefficient and less reliable results. The proposed study in this paper may provide a solution regarding the long-term wind speed forecast in order to solve the earlier-mentioned problems. For this purpose, two fundamentally different approaches, the statistical and the neural network-based approaches, have been developed to predict hourly wind speed data of the subsequent year. The novelty of this study is to forecast the general trend of the incoming year by designing a data fusion algorithm through several neural networks. A set of recent wind speed measurement samples from two meteorological stations in Malaysia, namely Kuala Terengganu and Mersing, are used to train and test the data set. The result obtained by the proposed method has given rather promising results in view of the very small mean absolute error (MAE).