A direct prediction method for wind power ramp events considering the class imbalanced problem

Predicting wind power ramp events directly based on the historical ramp event time series has drawn increasing attention recently. But the class imbalance problem of the ramp event time series significantly affects the prediction accuracy of ramp events. In the present study, a layer oversampling (LOS) method is proposed considering the relation characteristics of wind power amplitudes and the occurrence frequency of wind power ramp events. Meanwhile, a hybrid sampling method of error bootstrap-LOS (EB-LOS) is proposed by combining LOS with the EB oversampling method. After balancing the samples of the ramp and nonramp events by using different sampling methods, the backpropagation neural network (BPNN), and the long short-term memory (LSTM) methods are employed to directly predict ramp events based on historical data collected from eight wind farms. Comparison results proved that the proposed EB-LOS method achieves the best prediction performance with an average recall of 0.8196 when using the BPNN model to directly predict ramp events. The best prediction performance of the EB-LOS method is also proved by using the LSTM model to directly predict ramp events.

Automated summary

Predicting wind power ramp events based on historical time series has gained attention recently. However, the class imbalance problem affects the prediction accuracy. This study proposes a novel method called LOS considering wind power amplitudes and occurrence frequency. A hybrid sampling method, EB-LOS, is also proposed. The results show that EB-LOS achieves the best prediction performance using the BPNN and LSTM models.