| Summary: | 碩士 === 國立清華大學 === 工業工程與工程管理學系 === 99 === Recently, energy shortage has become a significant issue that we must have to face. Hence, people now pay much more attention to renewable green energy than before. Nowadays, much renewable energy is being developed and applied to our lives, such as solar energy, water energy, wind energy, and hydrogen energy. Among the many kinds of renewable energy, in this study, we focused on wind power forecast, which has a low cost and is non-polluting. In this paper, our forecast model is based on an Artificial Neural Network (ANN) model; we seek the model solutions by Improved Simplified Swarm Optimization (ISSO). Before wind power forecast, we test our proposed model on five time series benchmark data set and compare the performance by mean square error (MSE) in order to verify the forecasting ability of our method. In the wind power forecast problem, the used data was collected at the Mai Liao wind farm in Taiwan over a period of five years from September 2002 to August 2007. In the experiment, we also carried out data pretreatment by performing a Principal Component Analysis (PCA) in order to increase the model efficiency. At last, we proved the forecasting results of our proposed method to be more precise than other methods by comparing the MSE.
|
|---|
