| Autor: |
Deockho Kim, Jin Hur, Hyuksoo Han |
| Předmět: |
|
| Zdroj: |
International Workshop on Large-Scale Integration of Wind Power into Power Systems as well as on Transmission Networks for Offshore Wind Plants; 2016, p729-735, 7p |
| Abstrakt: |
Wind power is the one of the sustainable energies which could be substituted for fossil fuel. Globally, wind capacity has increased more than 5 times during past 10 years. Since the wind power generation has an essentially intermittent and uncertain nature, grid operators have a risk of integration without the prediction. Therefore, the accurate wind power forecasting has an important role in the stable grid operation. We investigate the short-term wind power prediction model based on a statistical time series approach. In this paper, we propose the Autoregressive Integrated Moving Average with Exogenous Variables (ARIMAX) model to predict hourly wind power outputs. The augmented ARIMAX model is extended from Autoregressive Integrated Moving Average (ARIMA) model by adding exogenous such as a wind speed. We also apply the static learning period to reduce processing time which builds the predictive model, derives the forecast values and saves the memory. To validate our prediction model, we use the empirical wind data to establish prediction model from the Jeju's wind farm in Korea. The simulation results are compared with ones from ARIMA model. The augmented ARIMAX model will enhance the predictive accuracy. [ABSTRACT FROM AUTHOR] |
| Databáze: |
Complementary Index |
| Externí odkaz: |
|
