Multi-step short-term wind speed forecasting approach based on multi-scale dominant ingredient chaotic analysis, improved hybrid GWO-SCA optimization and ELM

Abstract

Accurate wind speed prediction possesses a significant impact on reasonable scheduling and safe operation of power system. For this purpose, a novel hybrid approach based on multi-scale dominant ingredient chaotic analysis, improved hybrid GWO-SCA (IHGWOSCA) algorithm and extreme learning machine (ELM) is proposed for multi-step short-term wind speed prediction, in which the multi-scale dominant ingredient chaotic analysis combines the proposed optimal variational mode decomposition (OVMD), singular spectrum analysis (SSA) and phase space reconstruction (PSR). To begin with, the mode number and updating step of VMD are pre-determined by center frequency observation method and the proposed least-squares error index (LSEI), thus decomposing the non-stationary wind speed series into a set of intrinsic mode functions (IMFs). Later, the extraction of the dominant ingredient and residuary ingredient for each sub-series is implemented by SSA for the construction of forecasting components. Subsequently, the proposed IHGWOSCA algorithm coded with discrete integers and real-valued are investigated to search optimal parameters in PSR and ELM successively. Lastly, the ultimate forecasting results of the original wind speed are calculated by accumulating results of all the predicted components. Furthermore, seven data sets from Sotavento Galicia and Inner Mongolia have been employed to evaluate the proposed approach. The results illustrate that: (1) the proposed OVMD-based models obtained better RMSE, MAE and MAPE indexes comparing with the benchmark models through weakening the non-stationary of the original signal; (2) the proposed dominant ingredient chaotic analysis combining SSA and PSR enhanced the multi-steps prediction performance effectively; (3) the proposed IHGWOSCA optimization algorithm possessed good capability for optimal parameters searching and fast convergence.