Stacking Ensemble Method with the RNN Meta-Learner for Short-Term PV Power Forecasting

Photovoltaic (PV) power forecasting urges in economic and secure operations of power systems. To avoid an inaccurate individual forecasting model, we propose an approach for a one-day to three-day ahead PV power hourly forecasting based on the stacking ensemble model with a recurrent neural network (RNN) as a meta-learner. The proposed approach is built by using real weather data and forecasted weather data in the training and testing stages, respectively. To accommodate uncertain weather, a daily clustering method based on statistical features, e.g., daily average, maximum, and standard deviation of PV power is applied in the data sets. Historical PV power output and weather data are used to train and test the model. The single learner considered in this research are artificial neural network, deep neural network, support vector regressions, long short-term memory, and convolutional neural network. Then, RNN is used to combine the forecasting results of each single learner. It is also important to observe the best combination of the single learners in this paper. Furthermore, to compare the performance of the proposed method, a random forest ensemble instead of RNN is used as a benchmark for comparison. Mean relative error (MRE) and mean absolute error (MAE) are used as criteria to validate the accuracy of different forecasting models. The MRE of the proposed RNN ensemble learner model is 4.29%, which has significant improvements by about 7-40%, 7-30%, and 8% compared to the single models, the combinations of fewer single learners, and the benchmark method, respectively. The results show that the proposed method is promising for use in real PV power forecasting systems.

Automated summary

The study introduces a PV power forecasting method based on a stacking ensemble model with recurrent neural network as a meta-learner, utilizing real and forecasted weather data for training and testing. By combining various statistical features and multiple neural network models for prediction, a more accurate forecasting result is achieved.