A Two-Tier Wind Power Time Series Model Considering Day-to-Day Weather Transition and Intraday Wind Power Fluctuations

A novel two-tier wind power time series model considering day-to-day weather transition and intraday wind power fluctuations is proposed. Weather factors and conditions are classified into typical weather states in terms of the effects on wind power using a fuzzy clustering technique. A typical weather Markov chain model is established to characterize day-to-day weather transition process. An improved Markov Chain Monte Carlo (MCMC) model considering the probability distributions of the wind power at the first time point of each day and wind power fluctuations is developed to characterize intraday wind power fluctuation process. The day-to-day typical weather Markov chain and intraday wind power time series for each typical weather state are simulated separately first and then integrated into a complete wind power time series. The proposed model is verified using the wind power records and weather data at an actual wind farm. The results indicate that different weather states have significantly different impacts on the distributions of daily average wind powers. The comparison analysis confirms that although the additional weather data inputs and the increase of model parameters are requisite, the proposed model outperforms the ARIMA model and the traditional MCMC model in terms of various accuracy indices.