On wavelet transform based convolutional neural network and twin support vector regression for wind power ramp event prediction

Power produced from renewable energy sources carbon negative and promises an increased reliability for grid integration. Wind sector globally has installed capacity of over 650 GW to grow substantially. In this work, wind power ramp events that arise sudden change in are studied. Forecasting is important problem statement the current industry. integration utility impacted by forecast accuracy. To improve security, speed forecasts extensively Ramp predicted manuscript using hybrid techniques employing wavelet decomposition transform tandem with convolutional neural network twin support vector machines. datasets Spain, Germany Argentina considered error metrics computed. It observed CNN based method 28.76% 26.43% superior random forest TSVR method.