Forecasting Short-Term Wind Speed Using ARIMA Model and ANN Model
碩士 === 國立勤益科技大學 === 工業工程與管理系 === 101 === The purpose of this study is to apply autoregressive integrated moving average (ARIMA) and automated neural networks (ANN) models to predict short-term wind speed. We collected the wind speed in a power plant in Taiwan. In addition to the ARIMA, the ANN is al...
| Main Authors: | , |
|---|---|
| Other Authors: | |
| Format: | Others |
| Language: | zh-TW |
| Published: |
2013
|
| Online Access: | http://ndltd.ncl.edu.tw/handle/65976644329930965279 |
| Summary: | 碩士 === 國立勤益科技大學 === 工業工程與管理系 === 101 === The purpose of this study is to apply autoregressive integrated moving average (ARIMA) and automated neural networks (ANN) models to predict short-term wind speed. We collected the wind speed in a power plant in Taiwan. In addition to the ARIMA, the ANN is also used to model and predict the wind speed that is collected every ten minutes. The prediction accuracy is determined by mean average error (MAE) and mean relative error (MRE) to determining.
We find that both of the MAE and MRE in ANN are smaller than those in the ARIMA. The results show that the ANN model is better than the ARIMA one in forecasting short-term wind speed.
|
|---|