A Fuzzy Group Forecasting Model Based on BPNN for Wind Power Output

Many forecasting models have been developed for forecasting wind farm electricity output. In most situations, performance of models is problem-dependent. Thus, it is difficult for forecasters to choose the right technique for each unique situation. In order to overcome this problem, this paper integrates multiple models into an aggregated model to obtain further performance improvement. Firstly, three groups of BPNN forecasting models are designed, i.e. univariate BPNN models, the hybrid model of ARIMA and BPNN and the multivariate model. Each group of the models can be regarded as an expert in forecasting, and then the fuzzy theory is used to combine all these forecasting results into the final answer. Results show that this group forecasting model performs well in terms of accuracy and consistency.