Short-Term Wind Power Generation Forecasting: Direct Versus Indirect Arima-Based Approaches

Abstract

Accurate prediction of short-term wind power generation is of great importance for wind farm operation, the balance of power grid load, and the optimization of bidding strategy on spot market. In general, wind power generation can be predicted using either direct prediction or indirect prediction approaches. The direct approach is to develop a forecasting model based on the historical wind power generation and then predict the future power generation. The indirect approach is to first obtain a wind speed forecasting model, make the prediction of future wind speed, and then convert wind speed forecast to wind power forecast based on the power curve of a wind turbine. This research compares the performances of the two approaches based on the wind speed and power production data of an offshore 2-MW wind turbine. The mature autoregressive integrated moving average (ARIMA)-family forecasting models are adopted for both approaches. In obtaining the forecasting models, no seasonality is found for both wind speed and wind power generation because of the relative short time span of data collection. Therefore, autoregressive and autoregressive moving average models, i.e., the simplified ARIMA models, turn out to be sufficient. The comparison shows that the direct approach produce significantly more accurate forecasts compared with the indirect approach in terms of both mean absolute error and root mean square error. The main reason is that the power curve only considers the averaged deterministic relationship between wind speed and power generation, while in reality the relationship is stochastic in nature. This variability leads to the lower accuracy in predicting wind power generation using the indirect approach.