In order to cope with the environmental problems of climate deterioration, reduce carbon emissions and develop environmentally friendly energy sources without delay. The global energy system is undergoing tremendous changes, accelerating the transformation of the energy structure, and promoting the development of the energy structure to a low-carbon or even carbon-free direction. Renewable energy has received attention due to its clean and green characteristics. Wind power generation, as an important way to develop renewable energy, faces grid security challenges due to the volatility and uncontrollability of wind speed. In this paper, a systematic prediction method is proposed for wind speed: the wind speed sequence is decomposed by the variational modal decomposition method according to the principle of envelope entropy, and the extreme learning machine network optimized by the bat algorithm is used to predict the data after decomposing. Besides, error sequence correction method based on kernel density estimation is proposed to predict residual. The availability of the model proposed in this paper is proved by experiments, and a good prediction effect is obtained. In order to heighten the utilization of wind energy, the wind power dispatching of relevant departments provides a reference method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.