Multi-step wind speed forecasting based on secondary decomposition algorithm and optimized back propagation neural network

• Published in: Applied soft computing Vol. 113; p. 107894
• Main Authors: Sun, Wei, Tan, Bin, Wang, Qiqi
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 01.12.2021
• Subjects: Back propagation neural network; Differential evolution; Secondary decomposition; Symplectic geometry mode decomposition; Wind speed prediction; Differential evolution; Wind speed prediction; Back propagation neural network; Secondary decomposition; Symplectic geometry mode decomposition
• ISSN: 1568-4946; 1872-9681
• DOI: 10.1016/j.asoc.2021.107894

Improve the reliability of wind speed forecasting is a crucial task in wind power generation. Due to the stochastic and noise nature of wind, a preprocessing step is beneficial for wind speed series to get clean data. The decomposition technique is reported as the critical preprocessor to transform the unstable wind speed data into several regular components. This study proposes a hybrid forecasting system, which combines secondary decomposition algorithm and optimized back propagation (BP) neural network. For the decomposition part, the variational mode decomposition (VMD) is firstly used to extract the low-frequency part from the original wind data. Then the symplectic geometry mode decomposition (SGMD) decomposes the rest high-frequency part into clean and separate components. The BP algorithm is optimized by the differential evolution (DE) as the predictor in this study. Empirical studies with different comparison models are conducted on real wind speed data. The results affirm the competitive strength of the proposed combination strategy. And the proposed two-stage decomposition technique is applicable for nonlinear wind speed analysis. •A new VMD-SGMD-DE-BP method is presented for wind speed forecasting.•A novel secondary decomposition algorithm VMD-SGMD is proposed for wind speed decomposition.•SGMD is specially applied to further decompose the high-frequency component generated by VMD.•The optimized hybrid model DE-BP is used to provide accurate prediction results.•Design multi-step wind speed forecasting in four actual experiments to examine the effectiveness.