A new compound structure combining DAWNN with modified water cycle algorithm-based synchronous optimization for wind speed forecasting

Abstract

With the aims to improve the forecasting performance, a novel hybrid model based on variational mode decomposition (VMD), phase space reconstruction (PSR), improved water cycle algorithm (WCA) and double activation function wavelet neural network (DAWNN) is established for wind speed forecasting. In the proposed wind speed forecasting model, VMD is firstly employed to decompose the original wind speed time series into different modes and PSR is utilized to construct appropriate input matrix of each mode for DAWNN. To take advantage of different activation functions, DAWNN with optimal combination of Mexican hat function and Morlet wavelet function is constructed to make short-term wind speed forecasting. Then, the proposed improved WCA based on the chaos initialization of population, exploration–exploitation synergy optimization strategy and adaptively adjusting the search intensity, is developed to optimize the reconstruction parameters of PSR, hidden node number and the weighted coefficients in DAWNN synchronously. To confirm and evaluate the forecasting performance of the proposed hybrid model, two sets of historical wind speed samples from a wind farm in China are employed to make multi-step short-term wind speed forecasting. The experimental results illustrate that the proposed compound structure is effective when applying in wind speed forecasting.