Wind power ramp prediction algorithm based on wavelet deep belief network

TL;DR

This paper introduces a hybrid wavelet deep belief network with adaptive feature selection for wind power ramp prediction, significantly improving accuracy and enhancing power grid safety.

Contribution

It presents a novel hybrid algorithm combining wavelet decomposition, adaptive feature selection, and deep belief networks for accurate wind power ramp prediction.

Findings

Prediction accuracy exceeds 90%

Effective in practical data scenarios

Improves power grid safety

Abstract

The wind power ramp events threaten the power grid safety significantly. To improve the ramp prediction accuracy, a hybrid wavelet deep belief network algorithm with adaptive feature selection (WDBNAFS) is proposed. First, the wind power characteristic is analyzed. Then, wavelet decomposition is addressed to the time series, and an adaptive feature selection algorithm is proposed to select the inputs of the prediction model. Finally, a deep belief network is employed to predict the wind power ramp event, and the proposed WDBNAFS was testified with the experiments based on the practical data. The simulation results demonstrate that the prediction accuracy of the proposed algorithm is more than 90%.